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]


Fast and Resource-Efficient Control of Wireless Cyber-Physical Systems
Fast and Resource-Efficient Control of Wireless Cyber-Physical Systems

Baumann, D.

KTH Royal Institute of Technology, Stockholm, Febuary 2019 (phdthesis)

ics

PDF [BibTex]

PDF [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
X-ray microscopic characterization of high-Tc-supercoductors using image processing

Bihler, M.

Universität Stuttgart, Stuttgart, 2019 (mastersthesis)

mms

[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
Novel X-ray lenses for direct and coherent imaging

Sanli, U. T.

Universität Stuttgart, Stuttgart, 2019 (phdthesis)

mms

link (url) DOI [BibTex]

link (url) DOI [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]


no image
Actively Learning Dynamical Systems with Gaussian Processes

Buisson-Fenet, M.

Mines ParisTech, PSL Research University, 2019 (mastersthesis)

Abstract
Predicting the behavior of complex systems is of great importance in many fields such as engineering, economics or meteorology. The evolution of such systems often follows a certain structure, which can be induced, for example from the laws of physics or of market forces. Mathematically, this structure is often captured by differential equations. The internal functional dependencies, however, are usually unknown. Hence, using machine learning approaches that recreate this structure directly from data is a promising alternative to designing physics-based models. In particular, for high dimensional systems with nonlinear effects, this can be a challenging task. Learning dynamical systems is different from the classical machine learning tasks, such as image processing, and necessitates different tools. Indeed, dynamical systems can be actuated, often by applying torques or voltages. Hence, the user has a power of decision over the system, and can drive it to certain states by going through the dynamics. Actuating this system generates data, from which a machine learning model of the dynamics can be trained. However, gathering informative data that is representative of the whole state space remains a challenging task. The question of active learning then becomes important: which control inputs should be chosen by the user so that the data generated during an experiment is informative, and enables efficient training of the dynamics model? In this context, Gaussian processes can be a useful framework for approximating system dynamics. Indeed, they perform well on small and medium sized data sets, as opposed to most other machine learning frameworks. This is particularly important considering data is often costly to generate and process, most of all when producing it involves actuating a complex physical system. Gaussian processes also yield a notion of uncertainty, which indicates how sure the model is about its predictions. In this work, we investigate in a principled way how to actively learn dynamical systems, by selecting control inputs that generate informative data. We model the system dynamics by a Gaussian process, and use information-theoretic criteria to identify control trajectories that maximize the information gain. Thus, the input space can be explored efficiently, leading to a data-efficient training of the model. We propose several methods, investigate their theoretical properties and compare them extensively in a numerical benchmark. The final method proves to be efficient at generating informative data. Thus, it yields the lowest prediction error with the same amount of samples on most benchmark systems. We propose several variants of this method, allowing the user to trade off computations with prediction accuracy, and show it is versatile enough to take additional objectives into account.

ics

[BibTex]

[BibTex]

2017


Human Shape Estimation using Statistical Body Models
Human Shape Estimation using Statistical Body Models

Loper, M. M.

University of Tübingen, May 2017 (thesis)

Abstract
Human body estimation methods transform real-world observations into predictions about human body state. These estimation methods benefit a variety of health, entertainment, clothing, and ergonomics applications. State may include pose, overall body shape, and appearance. Body state estimation is underconstrained by observations; ambiguity presents itself both in the form of missing data within observations, and also in the form of unknown correspondences between observations. We address this challenge with the use of a statistical body model: a data-driven virtual human. This helps resolve ambiguity in two ways. First, it fills in missing data, meaning that incomplete observations still result in complete shape estimates. Second, the model provides a statistically-motivated penalty for unlikely states, which enables more plausible body shape estimates. Body state inference requires more than a body model; we therefore build obser- vation models whose output is compared with real observations. In this thesis, body state is estimated from three types of observations: 3D motion capture markers, depth and color images, and high-resolution 3D scans. In each case, a forward process is proposed which simulates observations. By comparing observations to the results of the forward process, state can be adjusted to minimize the difference between simulated and observed data. We use gradient-based methods because they are critical to the precise estimation of state with a large number of parameters. The contributions of this work include three parts. First, we propose a method for the estimation of body shape, nonrigid deformation, and pose from 3D markers. Second, we present a concise approach to differentiating through the rendering process, with application to body shape estimation. And finally, we present a statistical body model trained from human body scans, with state-of-the-art fidelity, good runtime performance, and compatibility with existing animation packages.

ps

Official Version [BibTex]


no image
Computing with Uncertainty

Hennig, P.

2017 (mpi_year_book)

Abstract
Machine learning requires computer hardware to reliable and efficiently compute estimations for ever more complex and fundamentally incomputable quantities. A research team at MPI for Intelligent Systems in Tübingen develops new algorithms which purposely lower the precision of computations and return an explicit measure of uncertainty over the correct result alongside the estimate. Doing so allows for more flexible management of resources, and increases the reliability of intelligent systems.

link (url) DOI [BibTex]


no image
Biomechanics and Locomotion Control in Legged Animals and Legged Robots

Sproewitz, A., Heim, S.

2017 (mpi_year_book)

Abstract
An animal's running gait is dynamic, efficient, elegant, and adaptive. We see locomotion in animals as an orchestrated interplay of the locomotion apparatus, interacting with its environment. The Dynamic Locomotion Group at the Max Planck Institute for Intelligent Systems in Stuttgart develops novel legged robots to decipher aspects of biomechanics and neuromuscular control of legged locomotion in animals, and to understand general principles of locomotion.

link (url) DOI [BibTex]


Learning Inference Models for Computer Vision
Learning Inference Models for Computer Vision

Jampani, V.

MPI for Intelligent Systems and University of Tübingen, 2017 (phdthesis)

Abstract
Computer vision can be understood as the ability to perform 'inference' on image data. Breakthroughs in computer vision technology are often marked by advances in inference techniques, as even the model design is often dictated by the complexity of inference in them. This thesis proposes learning based inference schemes and demonstrates applications in computer vision. We propose techniques for inference in both generative and discriminative computer vision models. Despite their intuitive appeal, the use of generative models in vision is hampered by the difficulty of posterior inference, which is often too complex or too slow to be practical. We propose techniques for improving inference in two widely used techniques: Markov Chain Monte Carlo (MCMC) sampling and message-passing inference. Our inference strategy is to learn separate discriminative models that assist Bayesian inference in a generative model. Experiments on a range of generative vision models show that the proposed techniques accelerate the inference process and/or converge to better solutions. A main complication in the design of discriminative models is the inclusion of prior knowledge in a principled way. For better inference in discriminative models, we propose techniques that modify the original model itself, as inference is simple evaluation of the model. We concentrate on convolutional neural network (CNN) models and propose a generalization of standard spatial convolutions, which are the basic building blocks of CNN architectures, to bilateral convolutions. First, we generalize the existing use of bilateral filters and then propose new neural network architectures with learnable bilateral filters, which we call `Bilateral Neural Networks'. We show how the bilateral filtering modules can be used for modifying existing CNN architectures for better image segmentation and propose a neural network approach for temporal information propagation in videos. Experiments demonstrate the potential of the proposed bilateral networks on a wide range of vision tasks and datasets. In summary, we propose learning based techniques for better inference in several computer vision models ranging from inverse graphics to freely parameterized neural networks. In generative vision models, our inference techniques alleviate some of the crucial hurdles in Bayesian posterior inference, paving new ways for the use of model based machine learning in vision. In discriminative CNN models, the proposed filter generalizations aid in the design of new neural network architectures that can handle sparse high-dimensional data as well as provide a way for incorporating prior knowledge into CNNs.

ps

pdf [BibTex]

pdf [BibTex]


no image
Development and Evaluation of a Portable BCI System for Remote Data Acquisition

Emde, T.

Graduate School of Neural Information Processing, Eberhard Karls Universität Tübingen, Germany, 2017 (mastersthesis)

ei

[BibTex]

[BibTex]


no image
Brain-Computer Interfaces for patients with Amyotrophic Lateral Sclerosis

Fomina, T.

Eberhard Karls Universität Tübingen, Germany, 2017 (phdthesis)

ei

[BibTex]

[BibTex]


no image
Causal models for decision making via integrative inference

Geiger, P.

University of Stuttgart, Germany, 2017 (phdthesis)

ei

[BibTex]

[BibTex]


Capturing Hand-Object Interaction and Reconstruction of Manipulated Objects
Capturing Hand-Object Interaction and Reconstruction of Manipulated Objects

Tzionas, D.

University of Bonn, 2017 (phdthesis)

Abstract
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-priori 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 using RGB-D data. 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.

ps

Thesis link (url) Project Page [BibTex]


Evaluation of the passive dynamics of compliant legs with inertia
Evaluation of the passive dynamics of compliant legs with inertia

Györfi, B.

University of Applied Science Pforzheim, Germany, 2017 (mastersthesis)

dlg

[BibTex]

[BibTex]


no image
Learning Optimal Configurations for Modeling Frowning by Transcranial Electrical Stimulation

Sücker, K.

Graduate School of Neural Information Processing, Eberhard Karls Universität Tübingen, Germany, 2017 (mastersthesis)

ei

[BibTex]

[BibTex]


no image
Understanding FORC using synthetic micro-structured systems with variable coupling- and coercivefield distributions

Groß, Felix

Universität Stuttgart, Stuttgart, 2017 (mastersthesis)

mms

[BibTex]


no image
Adsorption von Wasserstoffmolekülen in nanoporösen Gerüststrukturen

Kotzur, Nadine

Universität Stuttgart, Stuttgart, 2017 (mastersthesis)

mms

[BibTex]

[BibTex]

2014


no image
Pole Balancing with Apollo

Holger Kaden

Eberhard Karls Universität Tübingen, December 2014 (mastersthesis)

am

[BibTex]

2014


[BibTex]


no image
Modeling the polygenic architecture of complex traits

Rakitsch, Barbara

Eberhard Karls Universität Tübingen, November 2014 (phdthesis)

ei

[BibTex]

[BibTex]


no image
Learning Coupling Terms for Obstacle Avoidance

Rai, A.

École polytechnique fédérale de Lausanne, August 2014 (mastersthesis)

am

Project Page [BibTex]

Project Page [BibTex]


no image
Object Tracking in Depth Images Using Sigma Point Kalman Filters

Issac, J.

Karlsruhe Institute of Technology, July 2014 (mastersthesis)

am

Project Page [BibTex]

Project Page [BibTex]


Modeling the Human Body in 3D: Data Registration and Human Shape Representation
Modeling the Human Body in 3D: Data Registration and Human Shape Representation

Tsoli, A.

Brown University, Department of Computer Science, May 2014 (phdthesis)

ps

pdf [BibTex]

pdf [BibTex]


no image
A Novel Causal Inference Method for Time Series

Shajarisales, N.

Eberhard Karls Universität Tübingen, Germany, Eberhard Karls Universität Tübingen, Germany, 2014 (mastersthesis)

ei

PDF [BibTex]

PDF [BibTex]


no image
A global analysis of extreme events and consequences for the terrestrial carbon cycle

Zscheischler, J.

Diss. No. 22043, ETH Zurich, Switzerland, ETH Zurich, Switzerland, 2014 (phdthesis)

ei

[BibTex]

[BibTex]


no image
Learning objective functions for autonomous motion generation

Kalakrishnan, M.

University of Southern California, University of Southern California, Los Angeles, CA, 2014 (phdthesis)

am

Project Page Project Page [BibTex]

Project Page Project Page [BibTex]


no image
Development of advanced methods for improving astronomical images

Schmeißer, N.

Eberhard Karls Universität Tübingen, Germany, Eberhard Karls Universität Tübingen, Germany, 2014 (diplomathesis)

ei

[BibTex]

[BibTex]


no image
The Feasibility of Causal Discovery in Complex Systems: An Examination of Climate Change Attribution and Detection

Lacosse, E.

Graduate Training Centre of Neuroscience, University of Tübingen, Germany, Graduate Training Centre of Neuroscience, University of Tübingen, Germany, 2014 (mastersthesis)

ei

[BibTex]

[BibTex]


no image
Causal Discovery in the Presence of Time-Dependent Relations or Small Sample Size

Huang, B.

Graduate Training Centre of Neuroscience, University of Tübingen, Germany, Graduate Training Centre of Neuroscience, University of Tübingen, Germany, 2014 (mastersthesis)

ei

[BibTex]

[BibTex]


no image
Exploring complex diseases with intelligent systems

Borgwardt, K.

2014 (mpi_year_book)

Abstract
Physicians are collecting an ever increasing amount of data describing the health state of their patients. Is new knowledge about diseases hidden in this data, which could lead to better therapies? The field of Machine Learning in Biomedicine is concerned with the development of approaches which help to gain such insights from massive biomedical data.

link (url) [BibTex]


no image
The cellular life-death decision – how mitochondrial membrane proteins can determine cell fate

García-Sáez, Ana J.

2014 (mpi_year_book)

Abstract
Living organisms have a very effective method for eliminating cells that are no longer needed: programmed death. Researchers in the group of Ana García Sáez work with a protein called Bax, a key regulator of apoptosis that creates pores with a flexible diameter inside the outer mitochondrial membrane. This step inevitably triggers the final death of the cell. These insights into the role of important key enzymes in setting off apoptosis could provide useful for developing drugs that can directly influence apoptosis.

link (url) [BibTex]


Deep apprenticeship learning for playing video games
Deep apprenticeship learning for playing video games

Bogdanovic, M.

University of Oxford, 2014 (mastersthesis)

[BibTex]


no image
Analysis of Distance Functions in Graphs

Alamgir, M.

University of Hamburg, Germany, University of Hamburg, Germany, 2014 (phdthesis)

ei

[BibTex]

[BibTex]


no image
Data-driven autonomous manipulation

Pastor, P.

University of Southern California, University of Southern California, Los Angeles, CA, 2014 (phdthesis)

am

Project Page Project Page [BibTex]

Project Page Project Page [BibTex]


no image
Schalten der Polarität magnetischer Vortexkerne durch eine Zwei-Frequenzen Anregung und mittels direkter Einkopplung eines Stroms

Sproll, M.

Universität Stuttgart, Stuttgart (und Cuvillier Verlag, Göttingen), Stuttgart, 2014 (phdthesis)

mms

[BibTex]

[BibTex]


no image
Vortex-Kern-Korrelation in gekoppelten Systemen

Jüllig, P.

Universität Stuttgart, Stuttgart, 2014 (phdthesis)

mms

link (url) [BibTex]

link (url) [BibTex]