Header logo is


2019


Towards Geometric Understanding of Motion
Towards Geometric Understanding of Motion

Ranjan, A.

University of Tübingen, December 2019 (phdthesis)

Abstract

The motion of the world is inherently dependent on the spatial structure of the world and its geometry. Therefore, classical optical flow methods try to model this geometry to solve for the motion. However, recent deep learning methods take a completely different approach. They try to predict optical flow by learning from labelled data. Although deep networks have shown state-of-the-art performance on classification problems in computer vision, they have not been as effective in solving optical flow. The key reason is that deep learning methods do not explicitly model the structure of the world in a neural network, and instead expect the network to learn about the structure from data. We hypothesize that it is difficult for a network to learn about motion without any constraint on the structure of the world. Therefore, we explore several approaches to explicitly model the geometry of the world and its spatial structure in deep neural networks.

The spatial structure in images can be captured by representing it at multiple scales. To represent multiple scales of images in deep neural nets, we introduce a Spatial Pyramid Network (SpyNet). Such a network can leverage global information for estimating large motions and local information for estimating small motions. We show that SpyNet significantly improves over previous optical flow networks while also being the smallest and fastest neural network for motion estimation. SPyNet achieves a 97% reduction in model parameters over previous methods and is more accurate.

The spatial structure of the world extends to people and their motion. Humans have a very well-defined structure, and this information is useful in estimating optical flow for humans. To leverage this information, we create a synthetic dataset for human optical flow using a statistical human body model and motion capture sequences. We use this dataset to train deep networks and see significant improvement in the ability of the networks to estimate human optical flow.

The structure and geometry of the world affects the motion. Therefore, learning about the structure of the scene together with the motion can benefit both problems. To facilitate this, we introduce Competitive Collaboration, where several neural networks are constrained by geometry and can jointly learn about structure and motion in the scene without any labels. To this end, we show that jointly learning single view depth prediction, camera motion, optical flow and motion segmentation using Competitive Collaboration achieves state-of-the-art results among unsupervised approaches.

Our findings provide support for our hypothesis that explicit constraints on structure and geometry of the world lead to better methods for motion estimation.

ps

PhD Thesis [BibTex]

2019


PhD Thesis [BibTex]


Attacking Optical Flow
Attacking Optical Flow

Ranjan, A., Janai, J., Geiger, A., Black, M. J.

In International Conference on Computer Vision, November 2019 (inproceedings)

Abstract
Deep neural nets achieve state-of-the-art performance on the problem of optical flow estimation. Since optical flow is used in several safety-critical applications like self-driving cars, it is important to gain insights into the robustness of those techniques. Recently, it has been shown that adversarial attacks easily fool deep neural networks to misclassify objects. The robustness of optical flow networks to adversarial attacks, however, has not been studied so far. In this paper, we extend adversarial patch attacks to optical flow networks and show that such attacks can compromise their performance. We show that corrupting a small patch of less than 1% of the image size can significantly affect optical flow estimates. Our attacks lead to noisy flow estimates that extend significantly beyond the region of the attack, in many cases even completely erasing the motion of objects in the scene. While networks using an encoder-decoder architecture are very sensitive to these attacks, we found that networks using a spatial pyramid architecture are less affected. We analyse the success and failure of attacking both architectures by visualizing their feature maps and comparing them to classical optical flow techniques which are robust to these attacks. We also demonstrate that such attacks are practical by placing a printed pattern into real scenes.

avg ps

Video Project Page Paper Supplementary Material link (url) [BibTex]

Video Project Page Paper Supplementary Material link (url) [BibTex]


Learning to Reconstruct {3D} Human Pose and Shape via Model-fitting in the Loop
Learning to Reconstruct 3D Human Pose and Shape via Model-fitting in the Loop

Kolotouros, N., Pavlakos, G., Black, M. J., Daniilidis, K.

In International Conference on Computer Vision, October 2019 (inproceedings)

Abstract
Model-based human pose estimation is currently approached through two different paradigms. Optimization-based methods fit a parametric body model to 2D observations in an iterative manner, leading to accurate image-model alignments, but are often slow and sensitive to the initialization. In contrast, regression-based methods, that use a deep network to directly estimate the model parameters from pixels, tend to provide reasonable, but not pixel accurate, results while requiring huge amounts of supervision. In this work, instead of investigating which approach is better, our key insight is that the two paradigms can form a strong collaboration. A reasonable, directly regressed estimate from the network can initialize the iterative optimization making the fitting faster and more accurate. Similarly, a pixel accurate fit from iterative optimization can act as strong supervision for the network. This is the core of our proposed approach SPIN (SMPL oPtimization IN the loop). The deep network initializes an iterative optimization routine that fits the body model to 2D joints within the training loop, and the fitted estimate is subsequently used to supervise the network. Our approach is self-improving by nature, since better network estimates can lead the optimization to better solutions, while more accurate optimization fits provide better supervision for the network. We demonstrate the effectiveness of our approach in different settings, where 3D ground truth is scarce, or not available, and we consistently outperform the state-of-the-art model-based pose estimation approaches by significant margins.

ps

pdf code project [BibTex]

pdf code project [BibTex]


Resolving {3D} Human Pose Ambiguities with {3D} Scene Constraints
Resolving 3D Human Pose Ambiguities with 3D Scene Constraints

Hassan, M., Choutas, V., Tzionas, D., Black, M. J.

In International Conference on Computer Vision, pages: 2282-2292, October 2019 (inproceedings)

Abstract
To understand and analyze human behavior, we need to capture humans moving in, and interacting with, the world. Most existing methods perform 3D human pose estimation without explicitly considering the scene. We observe however that the world constrains the body and vice-versa. To motivate this, we show that current 3D human pose estimation methods produce results that are not consistent with the 3D scene. Our key contribution is to exploit static 3D scene structure to better estimate human pose from monocular images. The method enforces Proximal Relationships with Object eXclusion and is called PROX. To test this, we collect a new dataset composed of 12 different 3D scenes and RGB sequences of 20 subjects moving in and interacting with the scenes. We represent human pose using the 3D human body model SMPL-X and extend SMPLify-X to estimate body pose using scene constraints. We make use of the 3D scene information by formulating two main constraints. The interpenetration constraint penalizes intersection between the body model and the surrounding 3D scene. The contact constraint encourages specific parts of the body to be in contact with scene surfaces if they are close enough in distance and orientation. For quantitative evaluation we capture a separate dataset with 180 RGB frames in which the ground-truth body pose is estimated using a motion-capture system. We show quantitatively that introducing scene constraints significantly reduces 3D joint error and vertex error. Our code and data are available for research at https://prox.is.tue.mpg.de.

ps

pdf poster link (url) [BibTex]

pdf poster link (url) [BibTex]


End-to-end Learning for Graph Decomposition
End-to-end Learning for Graph Decomposition

Song, J., Andres, B., Black, M., Hilliges, O., Tang, S.

In International Conference on Computer Vision, October 2019 (inproceedings)

Abstract
Deep neural networks provide powerful tools for pattern recognition, while classical graph algorithms are widely used to solve combinatorial problems. In computer vision, many tasks combine elements of both pattern recognition and graph reasoning. In this paper, we study how to connect deep networks with graph decomposition into an end-to-end trainable framework. More specifically, the minimum cost multicut problem is first converted to an unconstrained binary cubic formulation where cycle consistency constraints are incorporated into the objective function. The new optimization problem can be viewed as a Conditional Random Field (CRF) in which the random variables are associated with the binary edge labels. Cycle constraints are introduced into the CRF as high-order potentials. A standard Convolutional Neural Network (CNN) provides the front-end features for the fully differentiable CRF. The parameters of both parts are optimized in an end-to-end manner. The efficacy of the proposed learning algorithm is demonstrated via experiments on clustering MNIST images and on the challenging task of real-world multi-people pose estimation.

ps

PDF [BibTex]

PDF [BibTex]


Three-D Safari: Learning to Estimate Zebra Pose, Shape, and Texture from Images "In the Wild"
Three-D Safari: Learning to Estimate Zebra Pose, Shape, and Texture from Images "In the Wild"

Zuffi, S., Kanazawa, A., Berger-Wolf, T., Black, M. J.

In International Conference on Computer Vision, October 2019 (inproceedings)

Abstract
We present the first method to perform automatic 3D pose, shape and texture capture of animals from images acquired in-the-wild. In particular, we focus on the problem of capturing 3D information about Grevy's zebras from a collection of images. The Grevy's zebra is one of the most endangered species in Africa, with only a few thousand individuals left. Capturing the shape and pose of these animals can provide biologists and conservationists with information about animal health and behavior. In contrast to research on human pose, shape and texture estimation, training data for endangered species is limited, the animals are in complex natural scenes with occlusion, they are naturally camouflaged, travel in herds, and look similar to each other. To overcome these challenges, we integrate the recent SMAL animal model into a network-based regression pipeline, which we train end-to-end on synthetically generated images with pose, shape, and background variation. Going beyond state-of-the-art methods for human shape and pose estimation, our method learns a shape space for zebras during training. Learning such a shape space from images using only a photometric loss is novel, and the approach can be used to learn shape in other settings with limited 3D supervision. Moreover, we couple 3D pose and shape prediction with the task of texture synthesis, obtaining a full texture map of the animal from a single image. We show that the predicted texture map allows a novel per-instance unsupervised optimization over the network features. This method, SMALST (SMAL with learned Shape and Texture) goes beyond previous work, which assumed manual keypoints and/or segmentation, to regress directly from pixels to 3D animal shape, pose and texture. Code and data are available at https://github.com/silviazuffi/smalst

ps

code pdf supmat iccv19 presentation Project Page [BibTex]


Markerless Outdoor Human Motion Capture Using Multiple Autonomous Micro Aerial Vehicles
Markerless Outdoor Human Motion Capture Using Multiple Autonomous Micro Aerial Vehicles

Saini, N., Price, E., Tallamraju, R., Enficiaud, R., Ludwig, R., Martinović, I., Ahmad, A., Black, M.

In International Conference on Computer Vision, October 2019 (inproceedings) Accepted

Abstract
Capturing human motion in natural scenarios means moving motion capture out of the lab and into the wild. Typical approaches rely on fixed, calibrated, cameras and reflective markers on the body, significantly limiting the motions that can be captured. To make motion capture truly unconstrained, we describe the first fully autonomous outdoor capture system based on flying vehicles. We use multiple micro-aerial-vehicles(MAVs), each equipped with a monocular RGB camera, an IMU, and a GPS receiver module. These detect the person, optimize their position, and localize themselves approximately. We then develop a markerless motion capture method that is suitable for this challenging scenario with a distant subject, viewed from above, with approximately calibrated and moving cameras. We combine multiple state-of-the-art 2D joint detectors with a 3D human body model and a powerful prior on human pose. We jointly optimize for 3D body pose and camera pose to robustly fit the 2D measurements. To our knowledge, this is the first successful demonstration of outdoor, full-body, markerless motion capture from autonomous flying vehicles.

ps

Code Data Video Paper Manuscript Project Page [BibTex]


Occupancy Flow: 4D Reconstruction by Learning Particle Dynamics
Occupancy Flow: 4D Reconstruction by Learning Particle Dynamics

Niemeyer, M., Mescheder, L., Oechsle, M., Geiger, A.

International Conference on Computer Vision, October 2019 (conference)

Abstract
Deep learning based 3D reconstruction techniques have recently achieved impressive results. However, while state-of-the-art methods are able to output complex 3D geometry, it is not clear how to extend these results to time-varying topologies. Approaches treating each time step individually lack continuity and exhibit slow inference, while traditional 4D reconstruction methods often utilize a template model or discretize the 4D space at fixed resolution. In this work, we present Occupancy Flow, a novel spatio-temporal representation of time-varying 3D geometry with implicit correspondences. Towards this goal, we learn a temporally and spatially continuous vector field which assigns a motion vector to every point in space and time. In order to perform dense 4D reconstruction from images or sparse point clouds, we combine our method with a continuous 3D representation. Implicitly, our model yields correspondences over time, thus enabling fast inference while providing a sound physical description of the temporal dynamics. We show that our method can be used for interpolation and reconstruction tasks, and demonstrate the accuracy of the learned correspondences. We believe that Occupancy Flow is a promising new 4D representation which will be useful for a variety of spatio-temporal reconstruction tasks.

avg

pdf poster suppmat code Project page video blog [BibTex]


Texture Fields: Learning Texture Representations in Function Space
Texture Fields: Learning Texture Representations in Function Space

Oechsle, M., Mescheder, L., Niemeyer, M., Strauss, T., Geiger, A.

International Conference on Computer Vision, October 2019 (conference)

Abstract
In recent years, substantial progress has been achieved in learning-based reconstruction of 3D objects. At the same time, generative models were proposed that can generate highly realistic images. However, despite this success in these closely related tasks, texture reconstruction of 3D objects has received little attention from the research community and state-of-the-art methods are either limited to comparably low resolution or constrained experimental setups. A major reason for these limitations is that common representations of texture are inefficient or hard to interface for modern deep learning techniques. In this paper, we propose Texture Fields, a novel texture representation which is based on regressing a continuous 3D function parameterized with a neural network. Our approach circumvents limiting factors like shape discretization and parameterization, as the proposed texture representation is independent of the shape representation of the 3D object. We show that Texture Fields are able to represent high frequency texture and naturally blend with modern deep learning techniques. Experimentally, we find that Texture Fields compare favorably to state-of-the-art methods for conditional texture reconstruction of 3D objects and enable learning of probabilistic generative models for texturing unseen 3D models. We believe that Texture Fields will become an important building block for the next generation of generative 3D models.

avg

pdf suppmat video poster blog Project Page [BibTex]


{AMASS}: Archive of Motion Capture as Surface Shapes
AMASS: Archive of Motion Capture as Surface Shapes

Mahmood, N., Ghorbani, N., Troje, N. F., Pons-Moll, G., Black, M. J.

International Conference on Computer Vision, pages: 5442-5451, October 2019 (conference)

Abstract
Large datasets are the cornerstone of recent advances in computer vision using deep learning. In contrast, existing human motion capture (mocap) datasets are small and the motions limited, hampering progress on learning models of human motion. While there are many different datasets available, they each use a different parameterization of the body, making it difficult to integrate them into a single meta dataset. To address this, we introduce AMASS, a large and varied database of human motion that unifies 15 different optical marker-based mocap datasets by representing them within a common framework and parameterization. We achieve this using a new method, MoSh++, that converts mocap data into realistic 3D human meshes represented by a rigged body model. Here we use SMPL [26], which is widely used and provides a standard skeletal representation as well as a fully rigged surface mesh. The method works for arbitrary marker-sets, while recovering soft-tissue dynamics and realistic hand motion. We evaluate MoSh++ and tune its hyper-parameters using a new dataset of 4D body scans that are jointly recorded with marker-based mocap. The consistent representation of AMASS makes it readily useful for animation, visualization, and generating training data for deep learning. Our dataset is significantly richer than previous human motion collections, having more than 40 hours of motion data, spanning over 300 subjects, more than 11000 motions, and is available for research at https://amass.is.tue.mpg.de/.

ps

code pdf suppl arxiv project website video poster AMASS_Poster [BibTex]


Learning to Train with Synthetic Humans
Learning to Train with Synthetic Humans

Hoffmann, D. T., Tzionas, D., Black, M. J., Tang, S.

In German Conference on Pattern Recognition (GCPR), September 2019 (inproceedings)

Abstract
Neural networks need big annotated datasets for training. However, manual annotation can be too expensive or even unfeasible for certain tasks, like multi-person 2D pose estimation with severe occlusions. A remedy for this is synthetic data with perfect ground truth. Here we explore two variations of synthetic data for this challenging problem; a dataset with purely synthetic humans, as well as a real dataset augmented with synthetic humans. We then study which approach better generalizes to real data, as well as the influence of virtual humans in the training loss. We observe that not all synthetic samples are equally informative for training, while the informative samples are different for each training stage. To exploit this observation, we employ an adversarial student-teacher framework; the teacher improves the student by providing the hardest samples for its current state as a challenge. Experiments show that this student-teacher framework outperforms all our baselines.

ps

pdf suppl poster link (url) [BibTex]

pdf suppl poster link (url) [BibTex]


The Influence of Visual Perspective on Body Size Estimation in Immersive Virtual Reality
The Influence of Visual Perspective on Body Size Estimation in Immersive Virtual Reality

Thaler, A., Pujades, S., Stefanucci, J. K., Creem-Regehr, S. H., Tesch, J., Black, M. J., Mohler, B. J.

In ACM Symposium on Applied Perception, September 2019 (inproceedings)

Abstract
The creation of realistic self-avatars that users identify with is important for many virtual reality applications. However, current approaches for creating biometrically plausible avatars that represent a particular individual require expertise and are time-consuming. We investigated the visual perception of an avatar’s body dimensions by asking males and females to estimate their own body weight and shape on a virtual body using a virtual reality avatar creation tool. In a method of adjustment task, the virtual body was presented in an HTC Vive head-mounted display either co-located with (first-person perspective) or facing (third-person perspective) the participants. Participants adjusted the body weight and dimensions of various body parts to match their own body shape and size. Both males and females underestimated their weight by 10-20% in the virtual body, but the estimates of the other body dimensions were relatively accurate and within a range of ±6%. There was a stronger influence of visual perspective on the estimates for males, but this effect was dependent on the amount of control over the shape of the virtual body, indicating that the results might be caused by where in the body the weight changes expressed themselves. These results suggest that this avatar creation tool could be used to allow participants to make a relatively accurate self-avatar in terms of adjusting body part dimensions, but not weight, and that the influence of visual perspective and amount of control needed over the body shape are likely gender-specific.

ps

pdf [BibTex]

pdf [BibTex]


Motion Planning for Multi-Mobile-Manipulator Payload Transport Systems
Motion Planning for Multi-Mobile-Manipulator Payload Transport Systems

Tallamraju, R., Salunkhe, D., Rajappa, S., Ahmad, A., Karlapalem, K., Shah, S. V.

In 15th IEEE International Conference on Automation Science and Engineering, IEEE, August 2019 (inproceedings) Accepted

ps

[BibTex]

[BibTex]


Competitive Collaboration: Joint Unsupervised Learning of Depth, Camera Motion, Optical Flow and Motion Segmentation
Competitive Collaboration: Joint Unsupervised Learning of Depth, Camera Motion, Optical Flow and Motion Segmentation

Ranjan, A., Jampani, V., Balles, L., Kim, K., Sun, D., Wulff, J., Black, M. J.

In Proceedings IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), IEEE International Conference on Computer Vision and Pattern Recognition (CVPR) 2019, June 2019 (inproceedings)

Abstract
We address the unsupervised learning of several interconnected problems in low-level vision: single view depth prediction, camera motion estimation, optical flow, and segmentation of a video into the static scene and moving regions. Our key insight is that these four fundamental vision problems are coupled through geometric constraints. Consequently, learning to solve them together simplifies the problem because the solutions can reinforce each other. We go beyond previous work by exploiting geometry more explicitly and segmenting the scene into static and moving regions. To that end, we introduce Competitive Collaboration, a framework that facilitates the coordinated training of multiple specialized neural networks to solve complex problems. Competitive Collaboration works much like expectation-maximization, but with neural networks that act as both competitors to explain pixels that correspond to static or moving regions, and as collaborators through a moderator that assigns pixels to be either static or independently moving. Our novel method integrates all these problems in a common framework and simultaneously reasons about the segmentation of the scene into moving objects and the static background, the camera motion, depth of the static scene structure, and the optical flow of moving objects. Our model is trained without any supervision and achieves state-of-the-art performance among joint unsupervised methods on all sub-problems.

ps

Paper link (url) Project Page Project Page [BibTex]

Paper link (url) Project Page Project Page [BibTex]


Taking a Deeper Look at the Inverse Compositional Algorithm
Taking a Deeper Look at the Inverse Compositional Algorithm

Lv, Z., Dellaert, F., Rehg, J. M., Geiger, A.

In Proceedings IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), IEEE International Conference on Computer Vision and Pattern Recognition (CVPR) 2019, June 2019 (inproceedings)

Abstract
In this paper, we provide a modern synthesis of the classic inverse compositional algorithm for dense image alignment. We first discuss the assumptions made by this well-established technique, and subsequently propose to relax these assumptions by incorporating data-driven priors into this model. More specifically, we unroll a robust version of the inverse compositional algorithm and replace multiple components of this algorithm using more expressive models whose parameters we train in an end-to-end fashion from data. Our experiments on several challenging 3D rigid motion estimation tasks demonstrate the advantages of combining optimization with learning-based techniques, outperforming the classic inverse compositional algorithm as well as data-driven image-to-pose regression approaches.

avg

pdf suppmat Video Project Page Poster [BibTex]

pdf suppmat Video Project Page Poster [BibTex]


Local Temporal Bilinear Pooling for Fine-grained Action Parsing
Local Temporal Bilinear Pooling for Fine-grained Action Parsing

Zhang, Y., Tang, S., Muandet, K., Jarvers, C., Neumann, H.

In Proceedings IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), IEEE International Conference on Computer Vision and Pattern Recognition (CVPR) 2019, June 2019 (inproceedings)

Abstract
Fine-grained temporal action parsing is important in many applications, such as daily activity understanding, human motion analysis, surgical robotics and others requiring subtle and precise operations in a long-term period. In this paper we propose a novel bilinear pooling operation, which is used in intermediate layers of a temporal convolutional encoder-decoder net. In contrast to other work, our proposed bilinear pooling is learnable and hence can capture more complex local statistics than the conventional counterpart. In addition, we introduce exact lower-dimension representations of our bilinear forms, so that the dimensionality is reduced with neither information loss nor extra computation. We perform intensive experiments to quantitatively analyze our model and show the superior performances to other state-of-the-art work on various datasets.

ei ps

Code video demo pdf link (url) [BibTex]

Code video demo pdf link (url) [BibTex]


Learning to Regress 3D Face Shape and Expression from an Image without 3D Supervision
Learning to Regress 3D Face Shape and Expression from an Image without 3D Supervision

Sanyal, S., Bolkart, T., Feng, H., Black, M. J.

In Proceedings IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), IEEE International Conference on Computer Vision and Pattern Recognition (CVPR) 2019, June 2019 (inproceedings)

Abstract
The estimation of 3D face shape from a single image must be robust to variations in lighting, head pose, expression, facial hair, makeup, and occlusions. Robustness requires a large training set of in-the-wild images, which by construction, lack ground truth 3D shape. To train a network without any 2D-to-3D supervision, we present RingNet, which learns to compute 3D face shape from a single image. Our key observation is that an individual’s face shape is constant across images, regardless of expression, pose, lighting, etc. RingNet leverages multiple images of a person and automatically detected 2D face features. It uses a novel loss that encourages the face shape to be similar when the identity is the same and different for different people. We achieve invariance to expression by representing the face using the FLAME model. Once trained, our method takes a single image and outputs the parameters of FLAME, which can be readily animated. Additionally we create a new database of faces “not quite in-the-wild” (NoW) with 3D head scans and high-resolution images of the subjects in a wide variety of conditions. We evaluate publicly available methods and find that RingNet is more accurate than methods that use 3D supervision. The dataset, model, and results are available for research purposes.

ps

code pdf preprint link (url) Project Page [BibTex]

code pdf preprint link (url) Project Page [BibTex]


MOTS: Multi-Object Tracking and Segmentation
MOTS: Multi-Object Tracking and Segmentation

Voigtlaender, P., Krause, M., Osep, A., Luiten, J., Sekar, B. B. G., Geiger, A., Leibe, B.

In Proceedings IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), IEEE International Conference on Computer Vision and Pattern Recognition (CVPR) 2019, June 2019 (inproceedings)

Abstract
This paper extends the popular task of multi-object tracking to multi-object tracking and segmentation (MOTS). Towards this goal, we create dense pixel-level annotations for two existing tracking datasets using a semi-automatic annotation procedure. Our new annotations comprise 65,213 pixel masks for 977 distinct objects (cars and pedestrians) in 10,870 video frames. For evaluation, we extend existing multi-object tracking metrics to this new task. Moreover, we propose a new baseline method which jointly addresses detection, tracking, and segmentation with a single convolutional network. We demonstrate the value of our datasets by achieving improvements in performance when training on MOTS annotations. We believe that our datasets, metrics and baseline will become a valuable resource towards developing multi-object tracking approaches that go beyond 2D bounding boxes.

avg

pdf suppmat Project Page Poster Video Project Page [BibTex]

pdf suppmat Project Page Poster Video Project Page [BibTex]


PointFlowNet: Learning Representations for Rigid Motion Estimation from Point Clouds
PointFlowNet: Learning Representations for Rigid Motion Estimation from Point Clouds

Behl, A., Paschalidou, D., Donne, S., Geiger, A.

In Proceedings IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), IEEE International Conference on Computer Vision and Pattern Recognition (CVPR) 2019, June 2019 (inproceedings)

Abstract
Despite significant progress in image-based 3D scene flow estimation, the performance of such approaches has not yet reached the fidelity required by many applications. Simultaneously, these applications are often not restricted to image-based estimation: laser scanners provide a popular alternative to traditional cameras, for example in the context of self-driving cars, as they directly yield a 3D point cloud. In this paper, we propose to estimate 3D motion from such unstructured point clouds using a deep neural network. In a single forward pass, our model jointly predicts 3D scene flow as well as the 3D bounding box and rigid body motion of objects in the scene. While the prospect of estimating 3D scene flow from unstructured point clouds is promising, it is also a challenging task. We show that the traditional global representation of rigid body motion prohibits inference by CNNs, and propose a translation equivariant representation to circumvent this problem. For training our deep network, a large dataset is required. Because of this, we augment real scans from KITTI with virtual objects, realistically modeling occlusions and simulating sensor noise. A thorough comparison with classic and learning-based techniques highlights the robustness of the proposed approach.

avg

pdf suppmat Project Page Poster Video [BibTex]

pdf suppmat Project Page Poster Video [BibTex]


Learning Joint Reconstruction of Hands and Manipulated Objects
Learning Joint Reconstruction of Hands and Manipulated Objects

Hasson, Y., Varol, G., Tzionas, D., Kalevatykh, I., Black, M. J., Laptev, I., Schmid, C.

In Proceedings IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), pages: 11807-11816, IEEE International Conference on Computer Vision and Pattern Recognition (CVPR) 2019, June 2019 (inproceedings)

Abstract
Estimating hand-object manipulations is essential for interpreting and imitating human actions. Previous work has made significant progress towards reconstruction of hand poses and object shapes in isolation. Yet, reconstructing hands and objects during manipulation is a more challenging task due to significant occlusions of both the hand and object. While presenting challenges, manipulations may also simplify the problem since the physics of contact restricts the space of valid hand-object configurations. For example, during manipulation, the hand and object should be in contact but not interpenetrate. In this work, we regularize the joint reconstruction of hands and objects with manipulation constraints. We present an end-to-end learnable model that exploits a novel contact loss that favors physically plausible hand-object constellations. Our approach improves grasp quality metrics over baselines, using RGB images as input. To train and evaluate the model, we also propose a new large-scale synthetic dataset, ObMan, with hand-object manipulations. We demonstrate the transferability of ObMan-trained models to real data.

ps

pdf suppl poster link (url) Project Page Project Page [BibTex]

pdf suppl poster link (url) Project Page Project Page [BibTex]


Connecting the Dots: Learning Representations for Active Monocular Depth Estimation
Connecting the Dots: Learning Representations for Active Monocular Depth Estimation

Riegler, G., Liao, Y., Donne, S., Koltun, V., Geiger, A.

In Proceedings IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), IEEE International Conference on Computer Vision and Pattern Recognition (CVPR) 2019, June 2019 (inproceedings)

Abstract
We propose a technique for depth estimation with a monocular structured-light camera, \ie, a calibrated stereo set-up with one camera and one laser projector. Instead of formulating the depth estimation via a correspondence search problem, we show that a simple convolutional architecture is sufficient for high-quality disparity estimates in this setting. As accurate ground-truth is hard to obtain, we train our model in a self-supervised fashion with a combination of photometric and geometric losses. Further, we demonstrate that the projected pattern of the structured light sensor can be reliably separated from the ambient information. This can then be used to improve depth boundaries in a weakly supervised fashion by modeling the joint statistics of image and depth edges. The model trained in this fashion compares favorably to the state-of-the-art on challenging synthetic and real-world datasets. In addition, we contribute a novel simulator, which allows to benchmark active depth prediction algorithms in controlled conditions.

avg

pdf suppmat Poster Project Page [BibTex]

pdf suppmat Poster Project Page [BibTex]


Learning Non-volumetric Depth Fusion using Successive Reprojections
Learning Non-volumetric Depth Fusion using Successive Reprojections

Donne, S., Geiger, A.

In Proceedings IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), IEEE International Conference on Computer Vision and Pattern Recognition (CVPR) 2019, June 2019 (inproceedings)

Abstract
Given a set of input views, multi-view stereopsis techniques estimate depth maps to represent the 3D reconstruction of the scene; these are fused into a single, consistent, reconstruction -- most often a point cloud. In this work we propose to learn an auto-regressive depth refinement directly from data. While deep learning has improved the accuracy and speed of depth estimation significantly, learned MVS techniques remain limited to the planesweeping paradigm. We refine a set of input depth maps by successively reprojecting information from neighbouring views to leverage multi-view constraints. Compared to learning-based volumetric fusion techniques, an image-based representation allows significantly more detailed reconstructions; compared to traditional point-based techniques, our method learns noise suppression and surface completion in a data-driven fashion. Due to the limited availability of high-quality reconstruction datasets with ground truth, we introduce two novel synthetic datasets to (pre-)train our network. Our approach is able to improve both the output depth maps and the reconstructed point cloud, for both learned and traditional depth estimation front-ends, on both synthetic and real data.

avg

pdf suppmat Project Page Video Poster blog [BibTex]

pdf suppmat Project Page Video Poster blog [BibTex]


Expressive Body Capture: 3D Hands, Face, and Body from a Single Image
Expressive Body Capture: 3D Hands, Face, and Body from a Single Image

Pavlakos, G., Choutas, V., Ghorbani, N., Bolkart, T., Osman, A. A. A., Tzionas, D., Black, M. J.

In Proceedings IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), pages: 10975-10985, IEEE International Conference on Computer Vision and Pattern Recognition (CVPR) 2019, June 2019 (inproceedings)

Abstract
To facilitate the analysis of human actions, interactions and emotions, we compute a 3D model of human body pose, hand pose, and facial expression from a single monocular image. To achieve this, we use thousands of 3D scans to train a new, unified, 3D model of the human body, SMPL-X, that extends SMPL with fully articulated hands and an expressive face. Learning to regress the parameters of SMPL-X directly from images is challenging without paired images and 3D ground truth. Consequently, we follow the approach of SMPLify, which estimates 2D features and then optimizes model parameters to fit the features. We improve on SMPLify in several significant ways: (1) we detect 2D features corresponding to the face, hands, and feet and fit the full SMPL-X model to these; (2) we train a new neural network pose prior using a large MoCap dataset; (3) we define a new interpenetration penalty that is both fast and accurate; (4) we automatically detect gender and the appropriate body models (male, female, or neutral); (5) our PyTorch implementation achieves a speedup of more than 8x over Chumpy. We use the new method, SMPLify-X, to fit SMPL-X to both controlled images and images in the wild. We evaluate 3D accuracy on a new curated dataset comprising 100 images with pseudo ground-truth. This is a step towards automatic expressive human capture from monocular RGB data. The models, code, and data are available for research purposes at https://smpl-x.is.tue.mpg.de.

ps

video code pdf suppl poster link (url) Project Page [BibTex]

video code pdf suppl poster link (url) Project Page [BibTex]


Capture, Learning, and Synthesis of 3D Speaking Styles
Capture, Learning, and Synthesis of 3D Speaking Styles

Cudeiro, D., Bolkart, T., Laidlaw, C., Ranjan, A., Black, M. J.

In Proceedings IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), IEEE International Conference on Computer Vision and Pattern Recognition (CVPR) 2019, June 2019 (inproceedings)

Abstract
Audio-driven 3D facial animation has been widely explored, but achieving realistic, human-like performance is still unsolved. This is due to the lack of available 3D datasets, models, and standard evaluation metrics. To address this, we introduce a unique 4D face dataset with about 29 minutes of 4D scans captured at 60 fps and synchronized audio from 12 speakers. We then train a neural network on our dataset that factors identity from facial motion. The learned model, VOCA (Voice Operated Character Animation) takes any speech signal as input—even speech in languages other than English—and realistically animates a wide range of adult faces. Conditioning on subject labels during training allows the model to learn a variety of realistic speaking styles. VOCA also provides animator controls to alter speaking style, identity-dependent facial shape, and pose (i.e. head, jaw, and eyeball rotations) during animation. To our knowledge, VOCA is the only realistic 3D facial animation model that is readily applicable to unseen subjects without retargeting. This makes VOCA suitable for tasks like in-game video, virtual reality avatars, or any scenario in which the speaker, speech, or language is not known in advance. We make the dataset and model available for research purposes at http://voca.is.tue.mpg.de.

ps

code Project Page video paper [BibTex]

code Project Page video paper [BibTex]


Superquadrics Revisited: Learning 3D Shape Parsing beyond Cuboids
Superquadrics Revisited: Learning 3D Shape Parsing beyond Cuboids

Paschalidou, D., Ulusoy, A. O., Geiger, A.

In Proceedings IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), IEEE International Conference on Computer Vision and Pattern Recognition (CVPR) 2019, June 2019 (inproceedings)

Abstract
Abstracting complex 3D shapes with parsimonious part-based representations has been a long standing goal in computer vision. This paper presents a learning-based solution to this problem which goes beyond the traditional 3D cuboid representation by exploiting superquadrics as atomic elements. We demonstrate that superquadrics lead to more expressive 3D scene parses while being easier to learn than 3D cuboid representations. Moreover, we provide an analytical solution to the Chamfer loss which avoids the need for computational expensive reinforcement learning or iterative prediction. Our model learns to parse 3D objects into consistent superquadric representations without supervision. Results on various ShapeNet categories as well as the SURREAL human body dataset demonstrate the flexibility of our model in capturing fine details and complex poses that could not have been modelled using cuboids.

avg

Project Page Poster suppmat pdf Video blog handout [BibTex]

Project Page Poster suppmat pdf Video blog handout [BibTex]


A Magnetically-Actuated Untethered Jellyfish-Inspired Soft Milliswimmer
A Magnetically-Actuated Untethered Jellyfish-Inspired Soft Milliswimmer

(Best Paper Award)

Ziyu Ren, T. W., Hu, W.

RSS 2019: Robotics: Science and Systems Conference, June 2019 (conference)

pi

[BibTex]

[BibTex]


Real-Time Dense Mapping for Self-Driving Vehicles using Fisheye Cameras
Real-Time Dense Mapping for Self-Driving Vehicles using Fisheye Cameras

Cui, Z., Heng, L., Yeo, Y. C., Geiger, A., Pollefeys, M., Sattler, T.

In Proceedings of the IEEE International Conference on Robotics and Automation (ICRA) 2019, IEEE, International Conference on Robotics and Automation, May 2019 (inproceedings)

Abstract
We present a real-time dense geometric mapping algorithm for large-scale environments. Unlike existing methods which use pinhole cameras, our implementation is based on fisheye cameras which have larger field of view and benefit some other tasks including Visual-Inertial Odometry, localization and object detection around vehicles. Our algorithm runs on in-vehicle PCs at 15 Hz approximately, enabling vision-only 3D scene perception for self-driving vehicles. For each synchronized set of images captured by multiple cameras, we first compute a depth map for a reference camera using plane-sweeping stereo. To maintain both accuracy and efficiency, while accounting for the fact that fisheye images have a rather low resolution, we recover the depths using multiple image resolutions. We adopt the fast object detection framework YOLOv3 to remove potentially dynamic objects. At the end of the pipeline, we fuse the fisheye depth images into the truncated signed distance function (TSDF) volume to obtain a 3D map. We evaluate our method on large-scale urban datasets, and results show that our method works well even in complex environments.

avg

pdf video poster Project Page [BibTex]

pdf video poster Project Page [BibTex]


Project AutoVision: Localization and 3D Scene Perception for an Autonomous Vehicle with a Multi-Camera System
Project AutoVision: Localization and 3D Scene Perception for an Autonomous Vehicle with a Multi-Camera System

Heng, L., Choi, B., Cui, Z., Geppert, M., Hu, S., Kuan, B., Liu, P., Nguyen, R. M. H., Yeo, Y. C., Geiger, A., Lee, G. H., Pollefeys, M., Sattler, T.

In Proceedings of the IEEE International Conference on Robotics and Automation (ICRA) 2019, IEEE, International Conference on Robotics and Automation, May 2019 (inproceedings)

Abstract
Project AutoVision aims to develop localization and 3D scene perception capabilities for a self-driving vehicle. Such capabilities will enable autonomous navigation in urban and rural environments, in day and night, and with cameras as the only exteroceptive sensors. The sensor suite employs many cameras for both 360-degree coverage and accurate multi-view stereo; the use of low-cost cameras keeps the cost of this sensor suite to a minimum. In addition, the project seeks to extend the operating envelope to include GNSS-less conditions which are typical for environments with tall buildings, foliage, and tunnels. Emphasis is placed on leveraging multi-view geometry and deep learning to enable the vehicle to localize and perceive in 3D space. This paper presents an overview of the project, and describes the sensor suite and current progress in the areas of calibration, localization, and perception.

avg

pdf [BibTex]

pdf [BibTex]


no image
Elastic modulus affects adhesive strength of gecko-inspired synthetics in variable temperature and humidity

Mitchell, CT, Drotlef, D, Dayan, CB, Sitti, M, Stark, AY

In INTEGRATIVE AND COMPARATIVE BIOLOGY, pages: E372-E372, OXFORD UNIV PRESS INC JOURNALS DEPT, 2001 EVANS RD, CARY, NC 27513 USA, March 2019 (inproceedings)

pi

[BibTex]

[BibTex]


no image
Gecko-inspired composite microfibers for reversible adhesion on smooth and rough surfaces

Drotlef, D., Dayan, C., Sitti, M.

In INTEGRATIVE AND COMPARATIVE BIOLOGY, pages: E58-E58, OXFORD UNIV PRESS INC JOURNALS DEPT, 2001 EVANS RD, CARY, NC 27513 USA, 2019 (inproceedings)

pi

[BibTex]

[BibTex]


Resisting Adversarial Attacks using Gaussian Mixture Variational Autoencoders
Resisting Adversarial Attacks using Gaussian Mixture Variational Autoencoders

Ghosh, P., Losalka, A., Black, M. J.

In Proc. AAAI, 2019 (inproceedings)

Abstract
Susceptibility of deep neural networks to adversarial attacks poses a major theoretical and practical challenge. All efforts to harden classifiers against such attacks have seen limited success till now. Two distinct categories of samples against which deep neural networks are vulnerable, ``adversarial samples" and ``fooling samples", have been tackled separately so far due to the difficulty posed when considered together. In this work, we show how one can defend against them both under a unified framework. Our model has the form of a variational autoencoder with a Gaussian mixture prior on the latent variable, such that each mixture component corresponds to a single class. We show how selective classification can be performed using this model, thereby causing the adversarial objective to entail a conflict. The proposed method leads to the rejection of adversarial samples instead of misclassification, while maintaining high precision and recall on test data. It also inherently provides a way of learning a selective classifier in a semi-supervised scenario, which can similarly resist adversarial attacks. We further show how one can reclassify the detected adversarial samples by iterative optimization.

ps

link (url) Project Page [BibTex]


From Variational to Deterministic Autoencoders
From Variational to Deterministic Autoencoders

Ghosh*, P., Sajjadi*, M. S. M., Vergari, A., Black, M. J., Schölkopf, B.

2019, *equal contribution (conference) Submitted

Abstract
Variational Autoencoders (VAEs) provide a theoretically-backed framework for deep generative models. However, they often produce “blurry” images, which is linked to their training objective. Sampling in the most popular implementation, the Gaussian VAE, can be interpreted as simply injecting noise to the input of a deterministic decoder. In practice, this simply enforces a smooth latent space structure. We challenge the adoption of the full VAE framework on this specific point in favor of a simpler, deterministic one. Specifically, we investigate how substituting stochasticity with other explicit and implicit regularization schemes can lead to a meaningful latent space without having to force it to conform to an arbitrarily chosen prior. To retrieve a generative mechanism for sampling new data points, we propose to employ an efficient ex-post density estimation step that can be readily adopted both for the proposed deterministic autoencoders as well as to improve sample quality of existing VAEs. We show in a rigorous empirical study that regularized deterministic autoencoding achieves state-of-the-art sample quality on the common MNIST, CIFAR-10 and CelebA datasets.

ei ps

arXiv [BibTex]


NoVA: Learning to See in Novel Viewpoints and Domains
NoVA: Learning to See in Novel Viewpoints and Domains

Coors, B., Condurache, A. P., Geiger, A.

In 2019 International Conference on 3D Vision (3DV), 2019 International Conference on 3D Vision (3DV), 2019 (inproceedings)

Abstract
Domain adaptation techniques enable the re-use and transfer of existing labeled datasets from a source to a target domain in which little or no labeled data exists. Recently, image-level domain adaptation approaches have demonstrated impressive results in adapting from synthetic to real-world environments by translating source images to the style of a target domain. However, the domain gap between source and target may not only be caused by a different style but also by a change in viewpoint. This case necessitates a semantically consistent translation of source images and labels to the style and viewpoint of the target domain. In this work, we propose the Novel Viewpoint Adaptation (NoVA) model, which enables unsupervised adaptation to a novel viewpoint in a target domain for which no labeled data is available. NoVA utilizes an explicit representation of the 3D scene geometry to translate source view images and labels to the target view. Experiments on adaptation to synthetic and real-world datasets show the benefit of NoVA compared to state-of-the-art domain adaptation approaches on the task of semantic segmentation.

avg

pdf suppmat poster video [BibTex]

pdf suppmat poster video [BibTex]


Occupancy Networks: Learning 3D Reconstruction in Function Space
Occupancy Networks: Learning 3D Reconstruction in Function Space

Mescheder, L., Oechsle, M., Niemeyer, M., Nowozin, S., Geiger, A.

In Proceedings IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), IEEE International Conference on Computer Vision and Pattern Recognition (CVPR) 2019, 2019 (inproceedings)

Abstract
With the advent of deep neural networks, learning-based approaches for 3D reconstruction have gained popularity. However, unlike for images, in 3D there is no canonical representation which is both computationally and memory efficient yet allows for representing high-resolution geometry of arbitrary topology. Many of the state-of-the-art learning-based 3D reconstruction approaches can hence only represent very coarse 3D geometry or are limited to a restricted domain. In this paper, we propose Occupancy Networks, a new representation for learning-based 3D reconstruction methods. Occupancy networks implicitly represent the 3D surface as the continuous decision boundary of a deep neural network classifier. In contrast to existing approaches, our representation encodes a description of the 3D output at infinite resolution without excessive memory footprint. We validate that our representation can efficiently encode 3D structure and can be inferred from various kinds of input. Our experiments demonstrate competitive results, both qualitatively and quantitatively, for the challenging tasks of 3D reconstruction from single images, noisy point clouds and coarse discrete voxel grids. We believe that occupancy networks will become a useful tool in a wide variety of learning-based 3D tasks.

avg

Code Video pdf suppmat Project Page blog [BibTex]

Code Video pdf suppmat Project Page blog [BibTex]

2014


Hough-based Object Detection with Grouped Features
Hough-based Object Detection with Grouped Features

Srikantha, A., Gall, J.

International Conference on Image Processing, pages: 1653-1657, Paris, France, IEEE International Conference on Image Processing , October 2014 (conference)

Abstract
Hough-based voting approaches have been successfully applied to object detection. While these methods can be efficiently implemented by random forests, they estimate the probability for an object hypothesis for each feature independently. In this work, we address this problem by grouping features in a local neighborhood to obtain a better estimate of the probability. To this end, we propose oblique classification-regression forests that combine features of different trees. We further investigate the benefit of combining independent and grouped features and evaluate the approach on RGB and RGB-D datasets.

ps

pdf poster DOI Project Page [BibTex]

2014


pdf poster DOI Project Page [BibTex]


Omnidirectional 3D Reconstruction in Augmented Manhattan Worlds
Omnidirectional 3D Reconstruction in Augmented Manhattan Worlds

Schoenbein, M., Geiger, A.

International Conference on Intelligent Robots and Systems, pages: 716 - 723, IEEE, Chicago, IL, USA, IEEE/RSJ International Conference on Intelligent Robots and System, October 2014 (conference)

Abstract
This paper proposes a method for high-quality omnidirectional 3D reconstruction of augmented Manhattan worlds from catadioptric stereo video sequences. In contrast to existing works we do not rely on constructing virtual perspective views, but instead propose to optimize depth jointly in a unified omnidirectional space. Furthermore, we show that plane-based prior models can be applied even though planes in 3D do not project to planes in the omnidirectional domain. Towards this goal, we propose an omnidirectional slanted-plane Markov random field model which relies on plane hypotheses extracted using a novel voting scheme for 3D planes in omnidirectional space. To quantitatively evaluate our method we introduce a dataset which we have captured using our autonomous driving platform AnnieWAY which we equipped with two horizontally aligned catadioptric cameras and a Velodyne HDL-64E laser scanner for precise ground truth depth measurements. As evidenced by our experiments, the proposed method clearly benefits from the unified view and significantly outperforms existing stereo matching techniques both quantitatively and qualitatively. Furthermore, our method is able to reduce noise and the obtained depth maps can be represented very compactly by a small number of image segments and plane parameters.

avg ps

pdf DOI [BibTex]

pdf DOI [BibTex]


Geckogripper: A soft, inflatable robotic gripper using gecko-inspired elastomer micro-fiber adhesives
Geckogripper: A soft, inflatable robotic gripper using gecko-inspired elastomer micro-fiber adhesives

Song, S., Majidi, C., Sitti, M.

In Intelligent Robots and Systems (IROS 2014), 2014 IEEE/RSJ International Conference on, pages: 4624-4629, September 2014 (inproceedings)

Abstract
This paper proposes GeckoGripper, a novel soft, inflatable gripper based on the controllable adhesion mechanism of gecko-inspired micro-fiber adhesives, to pick-and-place complex and fragile non-planar or planar parts serially or in parallel. Unlike previous fibrillar structures that use peel angle to control the manipulation of parts, we developed an elastomer micro-fiber adhesive that is fabricated on a soft, flexible membrane, increasing the adaptability to non-planar three-dimensional (3D) geometries and controllability in adhesion. The adhesive switching ratio (the ratio between the maximum and minimum adhesive forces) of the developed gripper was measured to be around 204, which is superior to previous works based on peel angle-based release control methods. Adhesion control mechanism based on the stretch of the membrane and superior adaptability to non-planar 3D geometries enable the micro-fibers to pick-and-place various 3D parts as shown in demonstrations.

pi

DOI [BibTex]

DOI [BibTex]


Human Pose Estimation with Fields of Parts
Human Pose Estimation with Fields of Parts

Kiefel, M., Gehler, P.

In Computer Vision – ECCV 2014, LNCS 8693, pages: 331-346, Lecture Notes in Computer Science, (Editors: Fleet, David and Pajdla, Tomas and Schiele, Bernt and Tuytelaars, Tinne), Springer, 13th European Conference on Computer Vision, September 2014 (inproceedings)

Abstract
This paper proposes a new formulation of the human pose estimation problem. We present the Fields of Parts model, a binary Conditional Random Field model designed to detect human body parts of articulated people in single images. The Fields of Parts model is inspired by the idea of Pictorial Structures, it models local appearance and joint spatial configuration of the human body. However the underlying graph structure is entirely different. The idea is simple: we model the presence and absence of a body part at every possible position, orientation, and scale in an image with a binary random variable. This results into a vast number of random variables, however, we show that approximate inference in this model is efficient. Moreover we can encode the very same appearance and spatial structure as in Pictorial Structures models. This approach allows us to combine ideas from segmentation and pose estimation into a single model. The Fields of Parts model can use evidence from the background, include local color information, and it is connected more densely than a kinematic chain structure. On the challenging Leeds Sports Poses dataset we improve over the Pictorial Structures counterpart by 5.5% in terms of Average Precision of Keypoints (APK).

ei ps

website pdf DOI Project Page [BibTex]

website pdf DOI Project Page [BibTex]


Capturing Hand Motion with an RGB-D Sensor, Fusing a Generative Model with Salient Points
Capturing Hand Motion with an RGB-D Sensor, Fusing a Generative Model with Salient Points

Tzionas, D., Srikantha, A., Aponte, P., Gall, J.

In German Conference on Pattern Recognition (GCPR), pages: 1-13, Lecture Notes in Computer Science, Springer, GCPR, September 2014 (inproceedings)

Abstract
Hand motion capture has been an active research topic in recent years, following the success of full-body pose tracking. Despite similarities, hand tracking proves to be more challenging, characterized by a higher dimensionality, severe occlusions and self-similarity between fingers. For this reason, most approaches rely on strong assumptions, like hands in isolation or expensive multi-camera systems, that limit the practical use. In this work, we propose a framework for hand tracking that can capture the motion of two interacting hands using only a single, inexpensive RGB-D camera. Our approach combines a generative model with collision detection and discriminatively learned salient points. We quantitatively evaluate our approach on 14 new sequences with challenging interactions.

ps

pdf Supplementary pdf Supplementary Material Project Page DOI Project Page [BibTex]

pdf Supplementary pdf Supplementary Material Project Page DOI Project Page [BibTex]


{OpenDR}: An Approximate Differentiable Renderer
OpenDR: An Approximate Differentiable Renderer

Loper, M. M., Black, M. J.

In Computer Vision – ECCV 2014, 8695, pages: 154-169, Lecture Notes in Computer Science, (Editors: D. Fleet and T. Pajdla and B. Schiele and T. Tuytelaars ), Springer International Publishing, 13th European Conference on Computer Vision, September 2014 (inproceedings)

Abstract
Inverse graphics attempts to take sensor data and infer 3D geometry, illumination, materials, and motions such that a graphics renderer could realistically reproduce the observed scene. Renderers, however, are designed to solve the forward process of image synthesis. To go in the other direction, we propose an approximate di fferentiable renderer (DR) that explicitly models the relationship between changes in model parameters and image observations. We describe a publicly available OpenDR framework that makes it easy to express a forward graphics model and then automatically obtain derivatives with respect to the model parameters and to optimize over them. Built on a new autodiff erentiation package and OpenGL, OpenDR provides a local optimization method that can be incorporated into probabilistic programming frameworks. We demonstrate the power and simplicity of programming with OpenDR by using it to solve the problem of estimating human body shape from Kinect depth and RGB data.

ps

pdf Code Chumpy Supplementary video of talk DOI Project Page [BibTex]

pdf Code Chumpy Supplementary video of talk DOI Project Page [BibTex]


Discovering Object Classes from Activities
Discovering Object Classes from Activities

Srikantha, A., Gall, J.

In European Conference on Computer Vision, 8694, pages: 415-430, Lecture Notes in Computer Science, (Editors: D. Fleet and T. Pajdla and B. Schiele and T. Tuytelaars ), Springer International Publishing, 13th European Conference on Computer Vision, September 2014 (inproceedings)

Abstract
In order to avoid an expensive manual labeling process or to learn object classes autonomously without human intervention, object discovery techniques have been proposed that extract visual similar objects from weakly labelled videos. However, the problem of discovering small or medium sized objects is largely unexplored. We observe that videos with activities involving human-object interactions can serve as weakly labelled data for such cases. Since neither object appearance nor motion is distinct enough to discover objects in these videos, we propose a framework that samples from a space of algorithms and their parameters to extract sequences of object proposals. Furthermore, we model similarity of objects based on appearance and functionality, which is derived from human and object motion. We show that functionality is an important cue for discovering objects from activities and demonstrate the generality of the model on three challenging RGB-D and RGB datasets.

ps

pdf anno poster DOI Project Page [BibTex]

pdf anno poster DOI Project Page [BibTex]


Probabilistic Progress Bars
Probabilistic Progress Bars

Kiefel, M., Schuler, C., Hennig, P.

In Conference on Pattern Recognition (GCPR), 8753, pages: 331-341, Lecture Notes in Computer Science, (Editors: Jiang, X., Hornegger, J., and Koch, R.), Springer, GCPR, September 2014 (inproceedings)

Abstract
Predicting the time at which the integral over a stochastic process reaches a target level is a value of interest in many applications. Often, such computations have to be made at low cost, in real time. As an intuitive example that captures many features of this problem class, we choose progress bars, a ubiquitous element of computer user interfaces. These predictors are usually based on simple point estimators, with no error modelling. This leads to fluctuating behaviour confusing to the user. It also does not provide a distribution prediction (risk values), which are crucial for many other application areas. We construct and empirically evaluate a fast, constant cost algorithm using a Gauss-Markov process model which provides more information to the user.

ei ps pn

website+code pdf DOI [BibTex]

website+code pdf DOI [BibTex]


Optical Flow Estimation with Channel Constancy
Optical Flow Estimation with Channel Constancy

Sevilla-Lara, L., Sun, D., Learned-Miller, E. G., Black, M. J.

In Computer Vision – ECCV 2014, 8689, pages: 423-438, Lecture Notes in Computer Science, (Editors: D. Fleet and T. Pajdla and B. Schiele and T. Tuytelaars ), Springer International Publishing, 13th European Conference on Computer Vision, September 2014 (inproceedings)

Abstract
Large motions remain a challenge for current optical flow algorithms. Traditionally, large motions are addressed using multi-resolution representations like Gaussian pyramids. To deal with large displacements, many pyramid levels are needed and, if an object is small, it may be invisible at the highest levels. To address this we decompose images using a channel representation (CR) and replace the standard brightness constancy assumption with a descriptor constancy assumption. CRs can be seen as an over-segmentation of the scene into layers based on some image feature. If the appearance of a foreground object differs from the background then its descriptor will be different and they will be represented in different layers.We create a pyramid by smoothing these layers, without mixing foreground and background or losing small objects. Our method estimates more accurate flow than the baseline on the MPI-Sintel benchmark, especially for fast motions and near motion boundaries.

ps

pdf DOI [BibTex]

pdf DOI [BibTex]


Modeling Blurred Video with Layers
Modeling Blurred Video with Layers

Wulff, J., Black, M. J.

In Computer Vision – ECCV 2014, 8694, pages: 236-252, Lecture Notes in Computer Science, (Editors: D. Fleet and T. Pajdla and B. Schiele and T. Tuytelaars ), Springer International Publishing, 13th European Conference on Computer Vision, September 2014 (inproceedings)

Abstract
Videos contain complex spatially-varying motion blur due to the combination of object motion, camera motion, and depth variation with fi nite shutter speeds. Existing methods to estimate optical flow, deblur the images, and segment the scene fail in such cases. In particular, boundaries between di fferently moving objects cause problems, because here the blurred images are a combination of the blurred appearances of multiple surfaces. We address this with a novel layered model of scenes in motion. From a motion-blurred video sequence, we jointly estimate the layer segmentation and each layer's appearance and motion. Since the blur is a function of the layer motion and segmentation, it is completely determined by our generative model. Given a video, we formulate the optimization problem as minimizing the pixel error between the blurred frames and images synthesized from the model, and solve it using gradient descent. We demonstrate our approach on synthetic and real sequences.

ps

pdf Supplemental Video Data DOI Project Page Project Page [BibTex]

pdf Supplemental Video Data DOI Project Page Project Page [BibTex]


Intrinsic Video
Intrinsic Video

Kong, N., Gehler, P. V., Black, M. J.

In Computer Vision – ECCV 2014, 8690, pages: 360-375, Lecture Notes in Computer Science, (Editors: D. Fleet and T. Pajdla and B. Schiele and T. Tuytelaars ), Springer International Publishing, 13th European Conference on Computer Vision, September 2014 (inproceedings)

Abstract
Intrinsic images such as albedo and shading are valuable for later stages of visual processing. Previous methods for extracting albedo and shading use either single images or images together with depth data. Instead, we define intrinsic video estimation as the problem of extracting temporally coherent albedo and shading from video alone. Our approach exploits the assumption that albedo is constant over time while shading changes slowly. Optical flow aids in the accurate estimation of intrinsic video by providing temporal continuity as well as putative surface boundaries. Additionally, we find that the estimated albedo sequence can be used to improve optical flow accuracy in sequences with changing illumination. The approach makes only weak assumptions about the scene and we show that it substantially outperforms existing single-frame intrinsic image methods. We evaluate this quantitatively on synthetic sequences as well on challenging natural sequences with complex geometry, motion, and illumination.

ps

pdf Supplementary Video DOI Project Page Project Page [BibTex]

pdf Supplementary Video DOI Project Page Project Page [BibTex]


Automated Detection of New or Evolving Melanocytic Lesions Using a {3D} Body Model
Automated Detection of New or Evolving Melanocytic Lesions Using a 3D Body Model

Bogo, F., Romero, J., Peserico, E., Black, M. J.

In Medical Image Computing and Computer-Assisted Intervention (MICCAI), 8673, pages: 593-600, Lecture Notes in Computer Science, (Editors: Golland, Polina and Hata, Nobuhiko and Barillot, Christian and Hornegger, Joachim and Howe, Robert), Spring International Publishing, Medical Image Computing and Computer-Assisted Intervention (MICCAI), September 2014 (inproceedings)

Abstract
Detection of new or rapidly evolving melanocytic lesions is crucial for early diagnosis and treatment of melanoma.We propose a fully automated pre-screening system for detecting new lesions or changes in existing ones, on the order of 2 - 3mm, over almost the entire body surface. Our solution is based on a multi-camera 3D stereo system. The system captures 3D textured scans of a subject at diff erent times and then brings these scans into correspondence by aligning them with a learned, parametric, non-rigid 3D body model. This means that captured skin textures are in accurate alignment across scans, facilitating the detection of new or changing lesions. The integration of lesion segmentation with a deformable 3D body model is a key contribution that makes our approach robust to changes in illumination and subject pose.

ps

pdf Poster DOI Project Page [BibTex]

pdf Poster DOI Project Page [BibTex]


Tracking using Multilevel Quantizations
Tracking using Multilevel Quantizations

Hong, Z., Wang, C., Mei, X., Prokhorov, D., Tao, D.

In Computer Vision – ECCV 2014, 8694, pages: 155-171, Lecture Notes in Computer Science, (Editors: D. Fleet and T. Pajdla and B. Schiele and T. Tuytelaars ), Springer International Publishing, 13th European Conference on Computer Vision, September 2014 (inproceedings)

Abstract
Most object tracking methods only exploit a single quantization of an image space: pixels, superpixels, or bounding boxes, each of which has advantages and disadvantages. It is highly unlikely that a common optimal quantization level, suitable for tracking all objects in all environments, exists. We therefore propose a hierarchical appearance representation model for tracking, based on a graphical model that exploits shared information across multiple quantization levels. The tracker aims to find the most possible position of the target by jointly classifying the pixels and superpixels and obtaining the best configuration across all levels. The motion of the bounding box is taken into consideration, while Online Random Forests are used to provide pixel- and superpixel-level quantizations and progressively updated on-the-fly. By appropriately considering the multilevel quantizations, our tracker exhibits not only excellent performance in non-rigid object deformation handling, but also its robustness to occlusions. A quantitative evaluation is conducted on two benchmark datasets: a non-rigid object tracking dataset (11 sequences) and the CVPR2013 tracking benchmark (50 sequences). Experimental results show that our tracker overcomes various tracking challenges and is superior to a number of other popular tracking methods.

ps

pdf DOI [BibTex]

pdf DOI [BibTex]


Human Pose Estimation: New Benchmark and State of the Art Analysis
Human Pose Estimation: New Benchmark and State of the Art Analysis

Andriluka, M., Pishchulin, L., Gehler, P., Schiele, B.

In Proceedings IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), pages: 3686 - 3693, IEEE, IEEE International Conference on Computer Vision and Pattern Recognition, June 2014 (inproceedings)

ps

pdf DOI Project Page Project Page Project Page [BibTex]

pdf DOI Project Page Project Page Project Page [BibTex]


{FAUST}: Dataset and evaluation for {3D} mesh registration
FAUST: Dataset and evaluation for 3D mesh registration

(Dataset Award, Eurographics Symposium on Geometry Processing (SGP), 2016)

Bogo, F., Romero, J., Loper, M., Black, M. J.

In Proceedings IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), pages: 3794 -3801, Columbus, Ohio, USA, IEEE International Conference on Computer Vision and Pattern Recognition, June 2014 (inproceedings)

Abstract
New scanning technologies are increasing the importance of 3D mesh data and the need for algorithms that can reliably align it. Surface registration is important for building full 3D models from partial scans, creating statistical shape models, shape retrieval, and tracking. The problem is particularly challenging for non-rigid and articulated objects like human bodies. While the challenges of real-world data registration are not present in existing synthetic datasets, establishing ground-truth correspondences for real 3D scans is difficult. We address this with a novel mesh registration technique that combines 3D shape and appearance information to produce high-quality alignments. We define a new dataset called FAUST that contains 300 scans of 10 people in a wide range of poses together with an evaluation methodology. To achieve accurate registration, we paint the subjects with high-frequency textures and use an extensive validation process to ensure accurate ground truth. We find that current shape registration methods have trouble with this real-world data. The dataset and evaluation website are available for research purposes at http://faust.is.tue.mpg.de.

ps

pdf Video Dataset Poster Talk DOI Project Page Project Page Project Page [BibTex]

pdf Video Dataset Poster Talk DOI Project Page Project Page Project Page [BibTex]


Model Transport: Towards Scalable Transfer Learning on Manifolds
Model Transport: Towards Scalable Transfer Learning on Manifolds

Freifeld, O., Hauberg, S., Black, M. J.

In Proceedings IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), pages: 1378 -1385, Columbus, Ohio, USA, IEEE Intenational Conference on Computer Vision and Pattern Recognition, June 2014 (inproceedings)

Abstract
We consider the intersection of two research fields: transfer learning and statistics on manifolds. In particular, we consider, for manifold-valued data, transfer learning of tangent-space models such as Gaussians distributions, PCA, regression, or classifiers. Though one would hope to simply use ordinary Rn-transfer learning ideas, the manifold structure prevents it. We overcome this by basing our method on inner-product-preserving parallel transport, a well-known tool widely used in other problems of statistics on manifolds in computer vision. At first, this straightforward idea seems to suffer from an obvious shortcoming: Transporting large datasets is prohibitively expensive, hindering scalability. Fortunately, with our approach, we never transport data. Rather, we show how the statistical models themselves can be transported, and prove that for the tangent-space models above, the transport “commutes” with learning. Consequently, our compact framework, applicable to a large class of manifolds, is not restricted by the size of either the training or test sets. We demonstrate the approach by transferring PCA and logistic-regression models of real-world data involving 3D shapes and image descriptors.

ps

pdf SupMat Video poster DOI Project Page [BibTex]

pdf SupMat Video poster DOI Project Page [BibTex]