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 the captured video sequences and provide a temporally coherent, super-resolved, view-independent appearance representation. I will further discuss how to exploit the interdependency of both geometry and appearance as separate modalities to enhance visual perception and finally how to decompose appearance representations into intrinsic components (shading & albedo) and super-resolve them jointly to allow for more realistic renderings.
Organizers: Despoina Paschalidou
Understanding people in images and videos is a problem studied intensively in computer vision. While continuous progress has been made, occlusions, cluttered background, complex poses and large variety of appearance remain challenging, especially for crowded scenes. In this talk, I will explore the algorithms and tools that enable computer to interpret people's position, motion and articulated poses in the real-world challenging images and videos.More specifically, I will discuss an optimization problem whose feasible solutions define a decomposition of a given graph. I will highlight the applications of this problem in computer vision, which range from multi-person tracking [1,2,3] to motion segmentation . I will also cover an extended optimization problem whose feasible solutions define a decomposition of a given graph and a labeling of its nodes with the application on multi-person pose estimation . Reference:  Subgraph Decomposition for Multi-Object Tracking; S. Tang, B. Andres, M. Andriluka and B. Schiele; CVPR 2015  Multi-Person Tracking by Multicut and Deep Matching; S. Tang, B. Andres, M. Andriluka and B. Schiele; arXiv 2016  Multi-Person Tracking by Lifted Multicut and Person Re-identification; S. Tang, B. Andres, M. Andriluka and B. Schiele  A Multi-cut Formulation for Joint Segmentation and Tracking of Multiple Objects; M. Keuper, S. Tang, Z. Yu, B. Andres, T. Brox and B. Schiele; arXiv 2016  DeepCut: Joint Subset Partition and Labeling for Multi Person Pose Estimation.: L. Pishchulin, E. Insafutdinov, S. Tang, B. Andres, M. Andriluka, P. Gehler and B. Schiele; CVPR16
Organizers: Naureen Mahmood
Coronary artery disease (CAD) is the single leading cause of death worldwide and Cardiac Computed Tomography Angiography (CCTA) is a non-invasive test to rule out CAD using the anatomical characterization of the coronary lesions. Recent studies suggest that coronary lesions’ hemodynamic significance can be assessed by Fractional Flow Reserve (FFR), which is usually measured invasively in the CathLab but can also be simulated from a patient-specific biophysical model based on CCTA data. We learn a parametric lumped model (LM) enabling fast computational fluid dynamic simulations of blood flow in elongated vessel networks to alleviate the computational burden of 3D finite element (FE) simulations. We adapt the coefficients balancing the local nonlinear hydraulic effects from a training set of precomputed FE simulations. Our LM yields accurate pressure predictions suggesting that costly FE simulations can be replaced by our fast LM paving the way to use a personalised interactive biophysical model with realtime feedback in clinical practice.
Hand motion capture with an RGB-D sensor gained recently a lot of research attention, however even most recent approaches focus on the case of a single isolated hand. We focus instead on hands that interact with other hands or with a rigid or articulated object. Our framework successfully captures motion in such scenarios by combining a generative model with discriminatively trained salient points, collision detection and physics simulation to achieve a low tracking error with physically plausible poses. All components are unified in a single objective function that can be optimized with standard optimization techniques. We initially assume a-priory knowledge of the object's shape and skeleton. In case of unknown object shape there are existing 3d reconstruction methods that capitalize on distinctive geometric or texture features. These methods though fail for textureless and highly symmetric objects like household articles, mechanical parts or toys. We show that extracting 3d hand motion for in-hand scanning effectively facilitates the reconstruction of such objects and we fuse the rich additional information of hands into a 3d reconstruction pipeline. Finally, although shape reconstruction is enough for rigid objects, there is a lack of tools that build rigged models of articulated objects that deform realistically. We propose a method that creates a fully rigged model consisting of a watertight mesh, embedded skeleton and skinning weights by employing a combination of deformable mesh tracking, motion segmentation based on spectral clustering and skeletonization based on mean curvature flow.
Organizers: Javier Romero
Matching between two sets arises in various areas in computer vision, such as feature point matching for 3D reconstruction, person re-identification for surveillance or data association for multi-target tracking. Most previous work focused either on designing suitable features and matching cost functions, or on developing faster and more accurate solvers for quadratic or higher-order problems. In the first part of my talk, I will present a strategy for improving state-of-the-art solutions by efficiently computing the marginals of the joint matching probability. The second part of my talk will revolve around our recent work on online multi-target tracking using recurrent neural networks (RNNs). I will mention some fundamental challenges we encountered and present our current solution.
The accurate reconstruction of facial shape is important for applications such as telepresence and gaming. It can be solved efficiently with the help of statistical shape models that constrain the shape of the reconstruction. In this talk, several methods to statistically analyze static and dynamic 3D face data are discussed. When statistically analyzing faces, various challenges arise from noisy, corrupt, or incomplete data. To overcome the limitations imposed by the poor data quality, we leverage redundancy in the data for shape processing. This is done by processing entire motion sequences in the case of dynamic data, and by jointly processing large databases in a groupwise fashion in the case of static data. First, a fully automatic approach to robustly register and statistically analyze facial motion sequences using a multilinear face model as statistical prior is proposed. Further, a statistical face model is discussed, which consists of many localized, decorrelated multilinear models. The localized and multi-scale nature of this model allows for recovery of fine-scale details while retaining robustness to severe noise and occlusions. Finally, the learning of statistical face models is formulated as a groupwise optimization framework that aims to learn a multilinear model while jointly optimizing the correspondence, or correcting the data.
In many control applications it is the goal to operate a dynamical system in an optimal way with respect to a certain performance criterion. In a combustion engine, for example, the goal could be to control the engine such that the emissions are minimized. Due to the complexity of an engine, the desired operating point is unknown or may even change over time so that it cannot be determined a priori. Extremum seeking control is a learning-control methodology to solve such kind of control problems. It is a model-free method that optimizes the steady-state behavior of a dynamical system. Since it can be implemented with very limited resources, it has found several applications in industry. In this talk we give an introduction to extremum seeking theory based on a recently developed framework which relies on tools from geometric control. Furthermore, we discuss how this framework can be utilized to solve distributed optimization and coordination problems in multi-agent systems.
Organizers: Sebastian Trimpe
I am studying the question how robots can autonomously develop skills. Considering children, it seems natural that they have their own agenda. They explore their environment in a playful way, without the necessity for somebody to tell them what to do next. With robots the situation is different. There are many methods to let robots learn to do something, but it is always about learning to do a specific task from a supervision signal. Unfortunately, these methods do not scale well to systems with many degrees of freedom, except a good prestructuring is available. The hypothesis is that if the robots first learn to use their bodies and interact with the environment in a playful way they can acquire many small skills with which they can later solve complicated tasks much quicker. In the talk I will present my steps into this direction. Starting from some general information theoretic consideration we provide robots with an own drive to do something and explore their behavioral capabilities. Technically this is achieved by considering the sensorimotor loop as a dynamical system, whose parameters are adapted online according to a gradient ascent on an approximated information quantity. I will show examples of simulated and real robots behaving in a self-determined way and present future directions of my research.
Organizers: Jane Walters
In the last decade, there has been a major shift in the perception, use and predicted applications of robots. In contrast to their early industrial counterparts, robots are envisioned to operate in increasingly complex and uncertain environments, alongside humans, and over long periods of time. In my talk, I will argue that machine learning is indispensable in order for this new generation of robots to achieve high performance. Based on various examples (and videos) ranging from aerial-vehicle dancing to ground-vehicle racing, I will demonstrate the effect of robot learning, and highlight how our learning algorithms intertwine model-based control with machine learning. In particular, I will focus on our latest work that provides guarantees during learning (for example, safety and robustness guarantees) by combining traditional controls methods (nonlinear, robust and model predictive control) with Gaussian process regression.
Organizers: Sebastian Trimpe
In this talk we present some recent results on human action recognition in videos. We, first, show how to use human pose for action recognition. To this end we propose a new pose-based convolutional neural network descriptor for action recognition, which aggregates motion and appearance information along tracks of human body parts. Next, we present an approach for spatio-temporal action localization in realistic videos. The approach first detects proposals at the frame-level and then tracks high-scoring proposals in the video. Our tracker relies simultaneously on instance-level and class-level detectors. Action are localized in time with a sliding window approach at the track level. Finally, we show how to extend this method to weakly supervised learning of actions, which allows to scale to large amounts of data without manual annotation.
Typical human actions such as hand-shaking and drinking last several seconds and exhibit characteristic spatio-temporal structure. Recent methods attempt to capture this structure and learn action representations with convolutional neural networks. Such representations, however, are typically learned at the level of single frames or short video clips and fail to model actions at their full temporal scale. In this work we learn video representations using neural networks with long-term temporal convolutions. We demonstrate that CNN models with increased temporal extents improve the accuracy of action recognition despite reduced spatial resolution. We also study the impact of different low-level representations, such as raw values of video pixels and optical flow vector fields and demonstrate the importance of high-quality optical flow estimation for learning accurate action models. We report state-of-the-art results on two challenging benchmarks for human action recognition UCF101 and HMDB51.