Events & Talks

Workshop 08-02-2018 - 09-02-2018 Second Max Planck ETH Workshop on Learning Control After a successful first edition in 2015, we are pleased to announce the second workshop on Learning Control within the Max Planck ETH Center for Learning Systems. The workshop will take place February 8-9 2018 at ETH Zurich. We cordially invite all researchers from ETH Zürich and MPI-IS interested in the area of Learning Control to participate and actively contribute to this workshop. Sebastian Trimpe Georg Martius Melanie Zeilinger

Haptic Intelligence Talk Haliza Mat Husin 19-01-2018 Maternal Weight and Metabolism Related to Fetal Autonomic Nervous System Background: Pre-pregnancy obesity and inadequate maternal weight gain during pregnancy can lead to adverse effects in the newborn but also to metabolic, cardiovascular and even neurological diseases in older ages of the offspring. Heart activity can be used as a proxy for the activity of the autonomic nervous system (ANS). The aim of this study is to evaluate the effect of pre-pregnancy weight, maternal weight gain and maternal metabolism on the ANS of the fetus in healthy pregnancies. Katherine J. Kuchenbecker

Autonomous Vision Talk Vagia Tsiminaki 15-12-2017 Appearance Modeling for 4D Multi-view Representations The emergence of multi-view capture systems has yield a tremendous amount of video sequences. The task of capturing spatio-temporal models from real world imagery (4D modeling) should arguably benefit from this enormous visual information. In order to achieve highly realistic representations both geometry and appearance need to be modeled in high precision. Yet, even with the great progress of the geometric modeling, the appearance aspect has not been fully explored and visual quality can still be improved. I will explain how we can optimally exploit the redundant visual information of ... Despoina Paschalidou

Empirical Inference Talk Robert Peharz 06-12-2017 Sum-Product Networks for Probabilistic Modeling Probabilistic modeling is the method of choice when it comes to reasoning under uncertainty. However, one of the main practical downsides of probabilistic models is that inference, i.e. the process of using the model to answer statistical queries, is notoriously hard in general. This led to a common folklore that probabilistic models which allow exact inference are necessarily simplistic and undermodel any practical task. In this talk, I will present sum-product networks (SPNs), a recently proposed architecture representing a rich and expressive class of probability distributions, which als...

Perceiving Systems Talk Dr. Gerard Pons-Moll 30-11-2017 Reconstructing and Perceiving Humans in Motion For man-machine interaction it is crucial to develop models of humans that look and move indistinguishably from real humans. Such virtual humans will be key for application areas such as computer vision, medicine and psychology, virtual and augmented reality and special effects in movies. Currently, digital models typically lack realistic soft tissue and clothing or require time-consuming manual editing of physical simulation parameters. Our hypothesis is that better and more realistic models of humans and clothing can be learned directly from real measurements coming from 4D scans, ima... Melanie Feldhofer

Haptic Intelligence IS Colloquium Professor Brent Gillespie 20-11-2017 Extending the Reafference and Internal Model Principles to Support Physical Human-Robot Interaction Relative to most robots and other machines, the human body is soft, its actuators compliant, and its control quite forgiving. But having a body that bends under load seems like a bad set-up for motor dexterity: the brain is faced with controlling more rather than fewer degrees of freedom. Undeniably, though, the soft body approach leads to superior solutions. Robots are putzes by comparison! While de-putzifying robots (perhaps by making them softer) is an endeavor I will discuss to some degree, in this talk I will focus on the design of robots intended to work cooperatively with humans, usi... Katherine J. Kuchenbecker

Autonomous Vision Talk Christoph Mayer 17-11-2017 Operator splitting: a versatile framework for variational image processing tasks. Variational image processing translates image processing tasks into optimisation problems. The practical success of this approach depends on the type of optimisation problem and on the properties of the ensuing algorithm. A recent breakthrough was to realise that old first-order optimisation algorithms based on operator splitting are particularly suited for modern data analysis problems. Operator splitting techniques decouple complex optimisation problems into many smaller and simpler sub-problems. In this talk I will revise the variational segmentation problem and a common family of al... Benjamin Coors

Perceiving Systems Symposium 29-10-2017 - 01-11-2017 Scenes from Video III This is the third in a series of invitation-only workshops held after ICCV. SfV brings together experts on image and video understanding, machine learning, and 3D scene analysis. In so doing, we hope to draw several lines of research together to address the problem of extracting both physical and semantic information from video. Michael Black

Autonomous Motion Talk Jens Kober 26-10-2017 Learning Complex Robot-Environment Interactions The acquisition and self-improvement of novel motor skills is among the most important problems in robotics. Reinforcement learning and imitation learning are two different but complimentary machine learning approaches commonly used for learning motor skills. Dieter Büchler

Empirical Inference IS Colloquium Simon Lacoste-Julien 23-10-2017 Modern Optimization for Structured Machine Learning Machine learning has become a popular application domain for modern optimization techniques, pushing its algorithmic frontier. The need for large scale optimization algorithms which can handle millions of dimensions or data points, typical for the big data era, have brought a resurgence of interest for first order algorithms, making us revisit the venerable stochastic gradient method [Robbins-Monro 1951] as well as the Frank-Wolfe algorithm [Frank-Wolfe 1956]. In this talk, I will review recent improvements on these algorithms which can exploit the structure of modern machine learning appro... Philipp Hennig

Autonomous Motion Talk Arunkumar Byravan 23-10-2017 Structured Deep Visual Dynamics Models for Robot Manipulation The ability to predict how an environment changes based on forces applied to it is fundamental for a robot to achieve specific goals. Traditionally in robotics, this problem is addressed through the use of pre-specified models or physics simulators, taking advantage of prior knowledge of the problem structure. While these models are general and have broad applicability, they depend on accurate estimation of model parameters such as object shape, mass, friction etc. On the other hand, learning based methods such as Predictive State Representations or more recent deep learning approaches have... Franzi Meier

Autonomous Vision Talk Michiel Vlaminck 20-10-2017 3D lidar mapping: an accurate and performant approach In my talk I will present my work regarding 3D mapping using lidar scanners. I will give an overview of the SLAM problem and its main challenges: robustness, accuracy and processing speed. Regarding robustness and accuracy, we investigate a better point cloud representation based on resampling and surface reconstruction. Moreover, we demonstrate how it can be incorporated in an ICP-based scan matching technique. Finally, we elaborate on globally consistent mapping using loop closures. Regarding processing speed, we propose the integration of our scan matching in a multi-resolution scheme an... Simon Donne

Autonomous Motion Talk Michael and Susan Leigh Anderson 20-10-2017 Machine Ethics We argue that ethically significant behavior of autonomous systems should be guided by explicit ethical principles determined through a consensus of ethicists. Such a consensus is likely to emerge in many areas in which autonomous systems are apt to be deployed and for the actions they are liable to undertake, as we are more likely to agree on how machines ought to treat us than on how human beings ought to treat one another. Given such a consensus, particular cases of ethical dilemmas where ethicists agree on the ethically relevant features and the right course of action can be used to hel... Vincent Berenz

Autonomous Vision Talk Slobodan Ilic and Mira Slavcheva 19-10-2017 SDF-2-SDF: 3D Reconstruction of Rigid and Deformable Objects from RGB-D Videos In this talk we will address the problem of 3D reconstruction of rigid and deformable objects from a single depth video stream. Traditional 3D registration techniques, such as ICP and its variants, are wide-spread and effective, but sensitive to initialization and noise due to the underlying correspondence estimation procedure. Therefore, we have developed SDF-2-SDF, a dense, correspondence-free method which aligns a pair of implicit representations of scene geometry, e.g. signed distance fields, by minimizing their direct voxel-wise difference. In its rigid variant, we apply it for static ... Fatma Güney

Empirical Inference IS Colloquium Dominik Bach 02-10-2017 Algorithms for survival: a decision-theoretic perspective on adaptive action under threat Under acute threat, biological agents need to choose adaptive actions to survive. In my talk, I will provide a decision-theoretic view on this problem and ask, what are potential computational algorithms for this choice, and how are they implemented in neural circuits. Rational design principles and non-human animal data tentatively suggest a specific architecture that heavily relies on tailored algorithms for specific threat scenarios. Virtual reality computer games provide an opportunity to translate non-human animal tasks to humans and investigate these algorithms across species. I will ... Michel Besserve

Perceiving Systems Talk Anton Van Den Hengel 02-10-2017 Visual Question Answering and why we’re asking the wrong question Visual Question Answering is one of the applications of Deep Learning that is pushing towards real Artificial Intelligence. It turns the typical deep learning process around by only defining the task to be carried out after the training has taken place, which changes the task fundamentally. We have developed a range of strategies for incorporating other information sources into deep learning-based methods, and the process taken a step towards developing algorithms which learn how to use other algorithms to solve a problem, rather than solving it directly. This talk thus covers some of the ... Siyu Tang

Talk Prof. Sami Haddadin 27-09-2017 The Gentle Robot Enabling robots for interaction with humans and unknown environments has been one of the primary goals of robotics research over decades. I will outline how human-centered robot design, nonlinear soft-robotics control inspired by human neuromechanics and physics grounded learning algorithms will let robots become a commodity in our near-future society. In particular, compliant and energy-controlled ultra-lightweight systems capable of complex collision handling enable high-performance human assistance over a wide variety of application domains. Together with novel methods for dynamics and s... Eva Lämmerhirt

Probabilistic Numerics IS Colloquium Amos Storkey 25-09-2017 Meta-learning statistics and augmentations for few shot learning In this talk I introduce the neural statistician as an approach for meta learning. The neural statistician learns to appropriately summarise datasets through a learnt statistic vector. This can be used for few shot learning, by computing the statistic vectors for the presented data, and using these statistics as context variables for one-shot classification and generation. I will show how we can generalise the neural statistician to a context aware learner that learns to characterise and combine independently learnt contexts. I will also demonstrate an approach for meta-learning data augmen... Philipp Hennig

IS Colloquium Prof. Amnon Shashua 18-09-2017 The Three Pillars of Fully Autonomous Driving The field of transportation is undergoing a seismic change with the coming introduction of autonomous driving. The technologies required to enable computer driven cars involves the latest cutting edge artificial intelligence algorithms along three major thrusts: Sensing, Planning and Mapping. Prof. Amnon Shashua, Co-founder and Chairman of Mobileye, will describe the challenges and the kind of machine learning algorithms involved, but will do that through the perspective of Mobileye’s activity in this domain. Michael Black

Max Planck Lecture Prof. Amnon Shashua 18-09-2017 The Three Pillars of Fully Autonomous Driving The field of transportation is undergoing a seismic change with the coming introduction of autonomous driving. The technologies required to enable computer driven cars involves the latest cutting edge artificial intelligence algorithms along three major thrusts: Sensing, Planning and Mapping. Prof. Amnon Shashua, Co-founder and Chairman of Mobileye, will describe the challenges and the kind of machine learning algorithms involved, but will do that through the perspective of Mobileye’s activity in this domain.

Autonomous Vision Event 07-09-2017 - 08-09-2017 AVG Summer Retreat

Probabilistic Numerics Talk Georgios Arvanitidis 05-09-2017 A locally Adaptive Normal Distribution The fundamental building block in many learning models is the distance measure that is used. Usually, the linear distance is used for simplicity. Replacing this stiff distance measure with a flexible one could potentially give a better representation of the actual distance between two points. I will present how the normal distribution changes if the distance measure respects the underlying structure of the data. In particular, a Riemannian manifold will be learned based on observations. The geodesic curve can then be computed—a length-minimizing curve under the Riemannian measure. With this... Philipp Hennig

Talk Prof. Dr. Hedvig Kjellström 25-08-2017 Developing an embodied agent to detect early signs of dementia In this talk I will first outline my different research projects. I will then focus on the EACare project, a quite newly started multi-disciplinary collaboration with the aim to develop an embodied system, capable of carrying out neuropsychological tests to detect early signs of dementia, e.g., due to Alzheimer's disease. The system will use methods from Machine Learning and Social Robotics, and be trained with examples of recorded clinician-patient interactions. The interaction will be developed using a participatory design approach. I describe the scope and method of the project, and repo...

Perceiving Systems Talk Yeara Kozlov 23-08-2017 Physical Blendshapes - Controllable Physics for Human Faces Creating convincing human facial animation is challenging. Face animation is often hand-crafted by artists separately from body motion. Alternatively, if the face animation is derived from motion capture, it is typically performed while the actor is relatively still. Recombining the isolated face animation with body motion is non-trivial and often results in uncanny results if the body dynamics are not properly reflected on the face (e.g. cheeks wiggling when running). In this talk, I will discuss the challenges of human soft tissue simulation and control. I will then present our method ... Timo Bolkart

Empirical Inference IS Colloquium Sanmi Koyejo 21-08-2017 Metrics Matter, Examples from Binary and Multilabel Classification Performance metrics are a key component of machine learning systems, and are ideally constructed to reflect real world tradeoffs. In contrast, much of the literature simply focuses on algorithms for maximizing accuracy. With the increasing integration of machine learning into real systems, it is clear that accuracy is an insufficient measure of performance for many problems of interest. Unfortunately, unlike accuracy, many real world performance metrics are non-decomposable i.e. cannot be computed as a sum of losses for each instance. Thus, known algorithms and associated analysis are not t... Mijung Park

Autonomous Motion Talk Mirko Bordignon 04-08-2017 Challenges of writing and maintaining programs for robots Writing and maintaining programs for robots poses some interesting challenges. It is hard to generalize them, as their targets are more than computing platforms. It can be deceptive to see them as input to output mappings, as interesting environments result in unpredictable inputs, and mixing reactive and deliberative behavior make intended outputs hard to define. Given the wide and fragmented landscape of components, from hardware to software, and the parties involved in providing and using them, integration is also a non-trivial aspect. The talk will illustrate the work ongoing at Fraunh... Vincent Berenz

Empirical Inference Talk Manfred K. Warmuth 25-07-2017 Low-dimensional Data Embedding via Robust Ranking Bernhard Schölkopf

Empirical Inference Talk Ioannis Papantonis 24-07-2017 Adaptive Learning Rate Algorithms for Stochastic Optimization and Variational Bayesian Inference We present a way to set the step size of Stochastic Gradient Descent, as the solution of a distance minimization problem. The obtained result has an intuitive interpretation and resembles the update rules of well known optimization algorithms. Also, asymptotic results to its relation to the optimal learning rate of Gradient Descent are discussed. In addition, we talk about two different estimators, with applications in Variational inference problems, and present approximate results about their variance. Finally, we combine all of the above, to present an optimization algorithm that... Philipp Hennig

Probabilistic Numerics IS Colloquium Azzurra Ruggeri 17-07-2017 Ecological learning: How children adapt their active learning strategies to achieve efficiency How do young children learn so much about the world, and so efficiently? This talk presents the recent studies investigating theoretically and empirically how children actively seek information in their physical and social environments as evidence to test and dynamically revise their hypotheses and theories over time. In particular, it will focus on how children adapt their active learning strategies. such as question-asking and explorative behavior, in response to the task characteristics, to the statistical structure of the hypothesis space, and to the feedback received. Such adaptiveness... Philipp Hennig Georg Martius

Autonomous Motion Workshop 16-07-2017 Articulated Model Tracking Workshop at the RSS (Robotics: Science and Systems Conference) at the Kresge Auditorium at the Massachusetts Institute of Technology in Cambridge, Massachusetts, USA. Jeannette Bohg

Autonomous Motion Workshop 15-07-2017 Revisiting Contact - Turning a Problem into a Solution Workshop July 17, 2017 during RSS (Robotics: Science and Systems Conference) at the Kresge Auditorium at the Massachusetts Institute of Technology in Cambridge, Massachusetts, USA. Jeannette Bohg

Autonomous Motion Workshop 15-07-2017 Women in Robotics III Workshop at the RSS (Robotics: Science and Systems Conference) at the Kresge Auditorium at the Massachusetts Institute of Technology in Cambridge, Massachusetts, USA. Jeannette Bohg

Autonomous Vision Talk Matteo Poggi 12-07-2017 Deep Learning for stereo matching and related tasks Recently, deep learning proved to be successful also on low level vision tasks such as stereo matching. Another recent trend in this latter field is represented by confidence measures, with increasing effectiveness when coupled with random forest classifiers or CNNs. Despite their excellent accuracy in outliers detection, few other applications rely on them. In the first part of the talk, we'll take a look at the latest proposal in terms of confidence measures for stereo matching, as well as at some novel methodologies exploiting these very accurate cues. In the second part, we'll talk ab... Yiyi Liao

Talk Prof. Andrew Blake 12-07-2017 Machines that learn to see and move Neural networks have taken the world of computing in general and AI in particular by storm. But in the future, AI will need to revisit generative models. There are several reasons for this – system robustness, precision, transparency, and the high cost of labelling data. This is particularly true of perceptual AI, as needed for autonomous vehicles, where also the need for simulators and the need to confront novel situations, also will demand generative, probabilistic models. Bernhard Schölkopf Michael Black Stefan Schaal

Empirical Inference Talk Prof. Stéphanie Lacour 11-07-2017 Soft bioelectronics: Materials and Technology Bioelectronics integrates principles of electrical engineering and materials science to biology, medicine and ultimately health. Soft bioelectronics focus on designing and manufacturing electronic devices with mechanical properties close to those of the host biological tissue so that long-term reliability and minimal perturbation are induced in vivo and/or truly wearable systems become possible. We illustrate the potential of this soft technology with examples ranging from prosthetic tactile skins to soft multimodal neural implants.

Empirical Inference Talk Chris Bauch 10-07-2017 Sentiment analysis of tweets to detect tipping points in vaccinating behaviour Vaccine refusal can lead to outbreaks of previously eradicated diseases and is an increasing problem worldwide. Vaccinating decisions exemplify a complex, coupled system where vaccinating behavior and disease dynamics influence one another. Complex systems often exhibit characteristic dynamics near a tipping point to a new dynamical regime. For instance, critical slowing down -- the tendency for a system to start `wobbling'-- can increase close to a tipping point. We used a linear support vector machine to classify the sentiment of geo-located United States and California tweets concern...

Talk Prof. Peer Fischer 06-07-2017 Micro Nano and Molecular Systems Lab: New Devices and Technologies This talk will look at hardware-based means of assembling, controlling and driving systems at the smallest of scales, including those that can become autonomous. I will show that insights from physics, chemistry and material engineering can be used to permit the simplification and miniaturization of otherwise bulky systems and that this can give rise to new technologies. One of the technologies we have invented may also permit the development of new imaging devices. Jane Walters Julia Braun

Talk Anastasia Pentina 05-07-2017 Multi-task Learning with Labeled and Unlabeled Tasks In multi-task learning, a learner is given a collection of prediction tasks and needs to solve all of them. In contrast to previous work, that required that annotated training data must be available for all tasks, I will talk about a new setting, in which for some tasks, potentially most of them, only unlabeled training data is available. Consequently, to solve all tasks, information must be transfered between tasks with labels and tasks without labels. Focussing on an instance-based transfer method I will consider two variants of this setting: when the set of labeled tasks i... Georg Martius

Probabilistic Numerics Talk Toni Karvonen 04-07-2017 Some parallels between classical and kernel quadrature This talk draws three parallels between classical algebraic quadrature rules, that are exact for polynomials of low degree, and kernel (or Bayesian) quadrature rules: i) Computational efficiency. Construction of scalable multivariate algebraic quadrature rules is challenging whereas kernel quadrature necessitates solving a linear system of equations, quickly becoming computationally prohibitive. Fully symmetric sets and Smolyak sparse grids can be used to solve both problems. ii) Derivatives and optimal rules. Algebraic degree of a Gaussian quadrature rule cannot be improved by adding deriv... Alexandra Gessner

Empirical Inference IS Colloquium Frederick Eberhardt 03-07-2017 Causal Macro Variables Standard methods of causal discovery take as input a statistical data set of measurements of well-defined causal variables. The goal is then to determine the causal relations among these variables. But how are these causal variables identified or constructed in the first place? Often we have sensor level data but assume that the relevant causal interactions occur at a higher scale of aggregation. Sometimes we only have aggregate measurements of causal interactions at a finer scale. I will motivate the general problem of causal discovery and present recent work on a framework and meth... Sebastian Weichwald

Talk Christoph Lampert 30-06-2017 Recent Projects on Lifelong Learning Georg Martius

Autonomous Motion Talk Omur Arslan 27-06-2017 Motion Planning via Reference Governors: Towards Closing the Gap Between High-Level and Low-Level Motion Planning In robotics, it is often practically and theoretically convenient to design motion planners for approximate simple robot and environment models first, and then adapt such reference planners to more accurate complex settings. In this talk, I will introduce a new approach to extend the applicability of motion planners of simple settings to more complex settings using reference governors. Reference governors are add-on control schemes for closed-loop dynamical systems to enforce constraint satisfaction while maintaining stability, and offers a systematic way of separating the issues of stabili... Stefan Schaal Lidia Pavel

Autonomous Motion Talk Sarah Bechtle 27-06-2017 On the Sense of Agency and of Object Permanence in Robots This work investigates the development of the sense of agency and of object permanence in humanoid robots. Based on findings from developmental psychology and from neuroscience, development of sense of object permanence is linked to development of sense of agency and to processes of internal simulation of sensor activity. In the course of the work, two sets of experiments will be presented, in the first set a humanoid robot has to learn the forward relationship between its movements and their sensory consequences perceived from the visual input. In particular, a self-monitoring mechanism w... Stefan Schaal Lidia Pavel

Perceiving Systems Talk Seong Joon Oh 22-06-2017 From understanding to controlling privacy against automatic person identification Growth of the internet and social media has spurred the sharing and dissemination of personal data at large scale. At the same time, recent developments in computer vision has enabled unseen effectiveness and efficiency in automated recognition. It is clear that visual data contains private information that can be mined, yet the privacy implications of sharing such data have been less studied in computer vision community. In the talk, I will present some key results from our study of the implications of the development of computer vision on the identifiability in social media, and an analys... Siyu Tang

Autonomous Vision Talk Matthias Niessner 14-06-2017 Reconstructing and Understanding 3D Indoor Environments In the recent years, commodity 3D sensors have become easily and widely available. These advances in sensing technology have spawned significant interest in using captured 3D data for mapping and semantic understanding of 3D environments. In this talk, I will give an overview of our latest research in the context of 3D reconstruction of indoor environments. I will further talk about the use of 3D data in the context of modern machine learning techniques. Specifically, I will highlight the importance of training data, and how can we efficiently obtain labeled and self-supervised ground truth... Despoina Paschalidou

Probabilistic Numerics Talk Jon Cockayne 13-06-2017 Bayesian Probabilistic Numerical Methods The emergent field of probabilistic numerics has thus far lacked rigorous statistical foundations. We establish that a class of Bayesian probabilistic numerical methods can be cast as the solution to certain non-standard Bayesian inverse problems. This allows us to establish general conditions under which Bayesian probabilistic numerical methods are well-defined, encompassing both non-linear models and non-Gaussian prior distributions. For general computation, a numerical approximation scheme is developed and its asymptotic convergence is established. The theoretical development is then ext... Michael Schober

Empirical Inference Talk Felix Leibfried and Jordi Grau-Moya 13-06-2017 Model-based reinforcement learning for sequential decision-making Autonomous systems rely on learning from experience to automatically refine their strategy and adapt to their environment, and thereby have huge advantages over traditional hand engineered systems. At PROWLER.io we use reinforcement learning (RL) for sequential decision making under uncertainty to develop intelligent agents capable of acting in dynamic and unknown environments. In this talk we first give a general overview of the goals and the research conducted at PROWLER.io. Then, we will talk about two specific research topics. The first is Information-Theoretic Model Uncertainty which d... Michel Besserve

Perceiving Systems Talk Nadine Rüegg 06-06-2017 From Camera Synchronization to Deep Learning We transfer a monocular motion stereo 3D reconstruction algorithm from a mobile device (Google Project Tango Tablet) to a rigidly mounted external camera of higher image resolution. A reliable camera synchronization is crucial for the usability of the tablets IMU data and thus a time synchronization method developed. It is based on the joint movement of the cameras. In a second project, we move from outdoor video scenes to aerial images and strive to segment them into polygonal shapes. While most existing approaches address the problem of automated generation of online maps as a pixel-wise... Siyu Tang

Talk Alexey Dosovitskiy 06-06-2017 Learning to see and act in dynamic three-dimensional environments Our world is dynamic and three-dimensional. Understanding the 3D layout of scenes and the motion of objects is crucial for successfully operating in such an environment. I will talk about two lines of recent research in this direction. One is on end-to-end learning of motion and 3D structure: optical flow estimation, binocular and monocular stereo, direct generation of large volumes with convolutional networks. The other is on sensorimotor control in immersive three-dimensional environments, learned from experience or from demonstration. Lars Mescheder Aseem Behl

Autonomous Vision Talk Alexey Dosovitskiy 06-06-2017 Learning to see and act in dynamic three-dimensional environments Our world is dynamic and three-dimensional. Understanding the 3D layout of scenes and the motion of objects is crucial for successfully operating in such an environment. I will talk about two lines of recent research in this direction. One is on end-to-end learning of motion and 3D structure: optical flow estimation, binocular and monocular stereo, direct generation of large volumes with convolutional networks. The other is on sensorimotor control in immersive three-dimensional environments, learned from experience or from demonstration. Lars Mescheder Aseem Behl

Research

Departments

Research Groups

People

Contact

Our Institute

Our History

Career

Doctoral Programs

Training

Service Units

Central Scientific Facilities

Workshops

Campus Services

Impact

Cooperation

Partners and Initiatives