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]


no image
Robot Learning for Muscular Robots

Büchler, D.

Technical University Darmstadt, Germany, December 2019 (phdthesis)

ei

[BibTex]

[BibTex]


no image
Real Time Probabilistic Models for Robot Trajectories

Gomez-Gonzalez, S.

Technical University Darmstadt, Germany, December 2019 (phdthesis)

ei

[BibTex]

[BibTex]


no image
Learning Transferable Representations

Rojas-Carulla, M.

University of Cambridge, UK, 2019 (phdthesis)

ei

[BibTex]

[BibTex]


no image
Sample-efficient deep reinforcement learning for continuous control

Gu, S.

University of Cambridge, UK, 2019 (phdthesis)

ei

[BibTex]


no image
Spatial Filtering based on Riemannian Manifold for Brain-Computer Interfacing

Xu, J.

Technical University of Munich, Germany, 2019 (mastersthesis)

ei

[BibTex]

[BibTex]


no image
Quantification of tumor heterogeneity using PET/MRI and machine learning

Katiyar, P.

Eberhard Karls Universität Tübingen, Germany, 2019 (phdthesis)

ei

[BibTex]

[BibTex]

2018


Model-based Optical Flow: Layers, Learning, and Geometry
Model-based Optical Flow: Layers, Learning, and Geometry

Wulff, J.

Tuebingen University, April 2018 (phdthesis)

Abstract
The estimation of motion in video sequences establishes temporal correspondences between pixels and surfaces and allows reasoning about a scene using multiple frames. Despite being a focus of research for over three decades, computing motion, or optical flow, remains challenging due to a number of difficulties, including the treatment of motion discontinuities and occluded regions, and the integration of information from more than two frames. One reason for these issues is that most optical flow algorithms only reason about the motion of pixels on the image plane, while not taking the image formation pipeline or the 3D structure of the world into account. One approach to address this uses layered models, which represent the occlusion structure of a scene and provide an approximation to the geometry. The goal of this dissertation is to show ways to inject additional knowledge about the scene into layered methods, making them more robust, faster, and more accurate. First, this thesis demonstrates the modeling power of layers using the example of motion blur in videos, which is caused by fast motion relative to the exposure time of the camera. Layers segment the scene into regions that move coherently while preserving their occlusion relationships. The motion of each layer therefore directly determines its motion blur. At the same time, the layered model captures complex blur overlap effects at motion discontinuities. Using layers, we can thus formulate a generative model for blurred video sequences, and use this model to simultaneously deblur a video and compute accurate optical flow for highly dynamic scenes containing motion blur. Next, we consider the representation of the motion within layers. Since, in a layered model, important motion discontinuities are captured by the segmentation into layers, the flow within each layer varies smoothly and can be approximated using a low dimensional subspace. We show how this subspace can be learned from training data using principal component analysis (PCA), and that flow estimation using this subspace is computationally efficient. The combination of the layered model and the low-dimensional subspace gives the best of both worlds, sharp motion discontinuities from the layers and computational efficiency from the subspace. Lastly, we show how layered methods can be dramatically improved using simple semantics. Instead of treating all layers equally, a semantic segmentation divides the scene into its static parts and moving objects. Static parts of the scene constitute a large majority of what is shown in typical video sequences; yet, in such regions optical flow is fully constrained by the depth structure of the scene and the camera motion. After segmenting out moving objects, we consider only static regions, and explicitly reason about the structure of the scene and the camera motion, yielding much better optical flow estimates. Furthermore, computing the structure of the scene allows to better combine information from multiple frames, resulting in high accuracies even in occluded regions. For moving regions, we compute the flow using a generic optical flow method, and combine it with the flow computed for the static regions to obtain a full optical flow field. By combining layered models of the scene with reasoning about the dynamic behavior of the real, three-dimensional world, the methods presented herein push the envelope of optical flow computation in terms of robustness, speed, and accuracy, giving state-of-the-art results on benchmarks and pointing to important future research directions for the estimation of motion in natural scenes.

ps

Official link DOI Project Page [BibTex]


no image
A virtual reality environment for experiments in assistive robotics and neural interfaces

Bustamante, S.

Graduate School of Neural Information Processing, Eberhard Karls Universität Tübingen, Germany, 2018 (mastersthesis)

ei

PDF [BibTex]

PDF [BibTex]


no image
Optimal Trajectory Generation and Learning Control for Robot Table Tennis

Koc, O.

Technical University Darmstadt, Germany, 2018 (phdthesis)

ei

[BibTex]

[BibTex]


no image
Distribution-Dissimilarities in Machine Learning

Simon-Gabriel, C. J.

Eberhard Karls Universität Tübingen, Germany, 2018 (phdthesis)

ei

[BibTex]

[BibTex]


no image
Domain Adaptation Under Causal Assumptions

Lechner, T.

Eberhard Karls Universität Tübingen, Germany, 2018 (mastersthesis)

ei

[BibTex]

[BibTex]


no image
A Causal Perspective on Deep Representation Learning

Suter, R.

ETH Zurich, 2018 (mastersthesis)

ei

[BibTex]


no image
Probabilistic Approaches to Stochastic Optimization

Mahsereci, M.

Eberhard Karls Universität Tübingen, Germany, 2018 (phdthesis)

ei pn

link (url) Project Page [BibTex]

link (url) Project Page [BibTex]


no image
Reinforcement Learning for High-Speed Robotics with Muscular Actuation

Guist, S.

Ruprecht-Karls-Universität Heidelberg , 2018 (mastersthesis)

ei

[BibTex]

[BibTex]


no image
Probabilistic Ordinary Differential Equation Solvers — Theory and Applications

Schober, M.

Eberhard Karls Universität Tübingen, Germany, 2018 (phdthesis)

ei pn

[BibTex]

[BibTex]


no image
A machine learning approach to taking EEG-based computer interfaces out of the lab

Jayaram, V.

Graduate Training Centre of Neuroscience, IMPRS, Eberhard Karls Universität Tübingen, Germany, 2018 (phdthesis)

ei

[BibTex]

[BibTex]

2016


Non-parametric Models for Structured Data and Applications to Human Bodies and Natural Scenes
Non-parametric Models for Structured Data and Applications to Human Bodies and Natural Scenes

Lehrmann, A.

ETH Zurich, July 2016 (phdthesis)

Abstract
The purpose of this thesis is the study of non-parametric models for structured data and their fields of application in computer vision. We aim at the development of context-sensitive architectures which are both expressive and efficient. Our focus is on directed graphical models, in particular Bayesian networks, where we combine the flexibility of non-parametric local distributions with the efficiency of a global topology with bounded treewidth. A bound on the treewidth is obtained by either constraining the maximum indegree of the underlying graph structure or by introducing determinism. The non-parametric distributions in the nodes of the graph are given by decision trees or kernel density estimators. The information flow implied by specific network topologies, especially the resultant (conditional) independencies, allows for a natural integration and control of contextual information. We distinguish between three different types of context: static, dynamic, and semantic. In four different approaches we propose models which exhibit varying combinations of these contextual properties and allow modeling of structured data in space, time, and hierarchies derived thereof. The generative character of the presented models enables a direct synthesis of plausible hypotheses. Extensive experiments validate the developed models in two application scenarios which are of particular interest in computer vision: human bodies and natural scenes. In the practical sections of this work we discuss both areas from different angles and show applications of our models to human pose, motion, and segmentation as well as object categorization and localization. Here, we benefit from the availability of modern datasets of unprecedented size and diversity. Comparisons to traditional approaches and state-of-the-art research on the basis of well-established evaluation criteria allows the objective assessment of our contributions.

ps

pdf [BibTex]

2015


no image
easyGWAS: An Integrated Computational Framework for Advanced Genome-Wide Association Studies

Grimm, Dominik

Eberhard Karls Universität Tübingen, November 2015 (phdthesis)

ei

[BibTex]

2015


[BibTex]


no image
Causal Discovery Beyond Conditional Independences

Sgouritsa, E.

Eberhard Karls Universität Tübingen, Germany, October 2015 (phdthesis)

ei

link (url) [BibTex]

link (url) [BibTex]


Proceedings of the 37th German Conference on Pattern Recognition
Proceedings of the 37th German Conference on Pattern Recognition

Gall, J., Gehler, P., Leibe, B.

Springer, German Conference on Pattern Recognition, October 2015 (proceedings)

ps

GCPR conference website [BibTex]

GCPR conference website [BibTex]


no image
From Points to Probability Measures: A Statistical Learning on Distributions with Kernel Mean Embedding

Muandet, K.

University of Tübingen, Germany, University of Tübingen, Germany, September 2015 (phdthesis)

ei

[BibTex]

[BibTex]


no image
Machine Learning Approaches to Image Deconvolution

Schuler, C.

University of Tübingen, Germany, University of Tübingen, Germany, September 2015 (phdthesis)

ei

[BibTex]

[BibTex]


no image
Blind Retrospective Motion Correction of MR Images

Loktyushin, A.

University of Tübingen, Germany, May 2015 (phdthesis)

ei

[BibTex]

[BibTex]


Shape Models of the Human Body for Distributed Inference
Shape Models of the Human Body for Distributed Inference

Zuffi, S.

Brown University, May 2015 (phdthesis)

Abstract
In this thesis we address the problem of building shape models of the human body, in 2D and 3D, which are realistic and efficient to use. We focus our efforts on the human body, which is highly articulated and has interesting shape variations, but the approaches we present here can be applied to generic deformable and articulated objects. To address efficiency, we constrain our models to be part-based and have a tree-structured representation with pairwise relationships between connected parts. This allows the application of methods for distributed inference based on message passing. To address realism, we exploit recent advances in computer graphics that represent the human body with statistical shape models learned from 3D scans. We introduce two articulated body models, a 2D model, named Deformable Structures (DS), which is a contour-based model parameterized for 2D pose and projected shape, and a 3D model, named Stitchable Puppet (SP), which is a mesh-based model parameterized for 3D pose, pose-dependent deformations and intrinsic body shape. We have successfully applied the models to interesting and challenging problems in computer vision and computer graphics, namely pose estimation from static images, pose estimation from video sequences, pose and shape estimation from 3D scan data. This advances the state of the art in human pose and shape estimation and suggests that carefully de ned realistic models can be important for computer vision. More work at the intersection of vision and graphics is thus encouraged.

ps

PDF [BibTex]


From Scans to Models: Registration of 3D Human Shapes Exploiting Texture Information
From Scans to Models: Registration of 3D Human Shapes Exploiting Texture Information

Bogo, F.

University of Padova, March 2015 (phdthesis)

Abstract
New scanning technologies are increasing the importance of 3D mesh data, and of algorithms that can reliably register meshes obtained from multiple scans. Surface registration is important e.g. for building full 3D models from partial scans, identifying and tracking objects in a 3D scene, creating statistical shape models. Human body registration is particularly important for many applications, ranging from biomedicine and robotics to the production of movies and video games; but obtaining accurate and reliable registrations is challenging, given the articulated, non-rigidly deformable structure of the human body. In this thesis, we tackle the problem of 3D human body registration. We start by analyzing the current state of the art, and find that: a) most registration techniques rely only on geometric information, which is ambiguous on flat surface areas; b) there is a lack of adequate datasets and benchmarks in the field. We address both issues. Our contribution is threefold. First, we present a model-based registration technique for human meshes that combines geometry and surface texture information to provide highly accurate mesh-to-mesh correspondences. Our approach estimates scene lighting and surface albedo, and uses the albedo to construct a high-resolution textured 3D body model that is brought into registration with multi-camera image data using a robust matching term. Second, by leveraging our technique, we present FAUST (Fine Alignment Using Scan Texture), a novel dataset collecting 300 high-resolution scans of 10 people in a wide range of poses. FAUST is the first dataset providing both real scans and automatically computed, reliable "ground-truth" correspondences between them. Third, we explore possible uses of our approach in dermatology. By combining our registration technique with a melanocytic lesion segmentation algorithm, we propose a system that automatically detects new or evolving lesions over almost the entire body surface, thus helping dermatologists identify potential melanomas. We conclude this thesis investigating the benefits of using texture information to establish frame-to-frame correspondences in dynamic monocular sequences captured with consumer depth cameras. We outline a novel approach to reconstruct realistic body shape and appearance models from dynamic human performances, and show preliminary results on challenging sequences captured with a Kinect.

ps

[BibTex]


Long Range Motion Estimation and Applications
Long Range Motion Estimation and Applications

Sevilla-Lara, L.

Long Range Motion Estimation and Applications, University of Massachusetts Amherst, University of Massachusetts Amherst, Febuary 2015 (phdthesis)

Abstract
Finding correspondences between images underlies many computer vision problems, such as optical flow, tracking, stereovision and alignment. Finding these correspondences involves formulating a matching function and optimizing it. This optimization process is often gradient descent, which avoids exhaustive search, but relies on the assumption of being in the basin of attraction of the right local minimum. This is often the case when the displacement is small, and current methods obtain very accurate results for small motions. However, when the motion is large and the matching function is bumpy this assumption is less likely to be true. One traditional way of avoiding this abruptness is to smooth the matching function spatially by blurring the images. As the displacement becomes larger, the amount of blur required to smooth the matching function becomes also larger. This averaging of pixels leads to a loss of detail in the image. Therefore, there is a trade-off between the size of the objects that can be tracked and the displacement that can be captured. In this thesis we address the basic problem of increasing the size of the basin of attraction in a matching function. We use an image descriptor called distribution fields (DFs). By blurring the images in DF space instead of in pixel space, we in- crease the size of the basin attraction with respect to traditional methods. We show competitive results using DFs both in object tracking and optical flow. Finally we demonstrate an application of capturing large motions for temporal video stitching.

ps

[BibTex]

[BibTex]


no image
A Cognitive Brain-Computer Interface for Patients with Amyotrophic Lateral Sclerosis

Hohmann, M.

Graduate Training Centre of Neuroscience, University of Tübingen, Germany, 2015 (mastersthesis)

ei

[BibTex]

[BibTex]


no image
Sequential Image Deconvolution Using Probabilistic Linear Algebra

Gao, M.

Technical University of Munich, Germany, 2015 (mastersthesis)

ei

[BibTex]

[BibTex]


no image
Causal Inference in Neuroimaging

Casarsa de Azevedo, L.

Graduate Training Centre of Neuroscience, University of Tübingen, Germany, 2015 (mastersthesis)

ei

[BibTex]

[BibTex]


no image
The effect of frowning on attention

Ibarra Chaoul, A.

Graduate Training Centre of Neuroscience, University of Tübingen, Germany, 2015 (mastersthesis)

ei

[BibTex]

[BibTex]

2008


no image
Reinforcement Learning for Motor Primitives

Kober, J.

Biologische Kybernetik, University of Stuttgart, Stuttgart, Germany, August 2008 (diplomathesis)

ei

PDF [BibTex]

2008


PDF [BibTex]


no image
Asymmetries of Time Series under Inverting their Direction

Peters, J.

Biologische Kybernetik, University of Heidelberg, August 2008 (diplomathesis)

ei

PDF [BibTex]

PDF [BibTex]


no image
Learning an Interest Operator from Human Eye Movements

Kienzle, W.

Biologische Kybernetik, Eberhard-Karls-Universität Tübingen, Tübingen, Germany, July 2008 (phdthesis)

ei

[BibTex]

[BibTex]


no image
CogRob 2008: The 6th International Cognitive Robotics Workshop

Lespérance, Y., Lakemeyer, G., Peters, J., Pirri, F.

Proceedings of the 6th International Cognitive Robotics Workshop (CogRob 2008), pages: 35, Patras University Press, Patras, Greece, 6th International Cognitive Robotics Workshop (CogRob), July 2008 (proceedings)

ei

Web [BibTex]

Web [BibTex]


no image
Causal inference from statistical data

Sun, X.

Biologische Kybernetik, Technische Hochschule Karlsruhe, Karlsruhe, Germany, April 2008 (phdthesis)

ei

Web [BibTex]

Web [BibTex]


no image
Pairwise Correlations and Multineuronal Firing Patterns in Primary Visual Cortex

Berens, P.

Biologische Kybernetik, Eberhard Karls Universität Tübingen, Tübingen, Germany, April 2008 (diplomathesis)

ei

[BibTex]

[BibTex]


no image
Development and Application of a Python Scripting Framework for BCI2000

Schreiner, T.

Biologische Kybernetik, Eberhard-Karls-Universität Tübingen, Tübingen, Germany, January 2008 (diplomathesis)

ei

[BibTex]

[BibTex]


no image
Efficient and Invariant Regularisation with Application to Computer Graphics

Walder, CJ.

Biologische Kybernetik, University of Queensland, Brisbane, Australia, January 2008 (phdthesis)

Abstract
This thesis develops the theory and practise of reproducing kernel methods. Many functional inverse problems which arise in, for example, machine learning and computer graphics, have been treated with practical success using methods based on a reproducing kernel Hilbert space perspective. This perspective is often theoretically convenient, in that many functional analysis problems reduce to linear algebra problems in these spaces. Somewhat more complex is the case of conditionally positive definite kernels, and we provide an introduction to both cases, deriving in a particularly elementary manner some key results for the conditionally positive definite case. A common complaint of the practitioner is the long running time of these kernel based algorithms. We provide novel ways of alleviating these problems by essentially using a non-standard function basis which yields computational advantages. That said, by doing so we must also forego the aforementioned theoretical conveniences, and hence need some additional analysis which we provide in order to make the approach practicable. We demonstrate that the method leads to state of the art performance on the problem of surface reconstruction from points. We also provide some analysis of kernels invariant to transformations such as translation and dilation, and show that this indicates the value of learning algorithms which use conditionally positive definite kernels. Correspondingly, we provide a few approaches for making such algorithms practicable. We do this either by modifying the kernel, or directly solving problems with conditionally positive definite kernels, which had previously only been solved with positive definite kernels. We demonstrate the advantage of this approach, in particular by attaining state of the art classification performance with only one free parameter.

ei

PDF [BibTex]

PDF [BibTex]