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 Systems

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
Reinforcement Learning for a Two-Robot Table Tennis Simulation

Li, G.

RWTH Aachen University, Germany, July 2019 (mastersthesis)

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

Bihler, M.

Universität Stuttgart, Stuttgart, 2019 (mastersthesis)

mms

[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]


Max Planck Institute for Intelligent Systems - Highlights
Max Planck Institute for Intelligent Systems - Highlights
2019 (mpi_year_book)

Abstract
In the future, artificially intelligent systems will substantially change the way we live, work, and communicate. Intelligent systems will become increasingly important in all spheres of life – as virtual systems on the Internet, or as cyber-physical systems in the real world. Artificial intelligence (AI) will be used for autonomous driving, as well as to diagnose and fight diseases, or to carry out emergency operations that are too dangerous for humans. This is just the beginning.

MPI IS Yearbook 2019 (en) MPI IS Jahresbericht 2019 (de) [BibTex]


no image
Ferromagnetic colloids in liquid crystal solvents

Zarubin, G.

Universität Stuttgart, Stuttgart, 2019 (phdthesis)

icm

link (url) DOI [BibTex]

link (url) DOI [BibTex]


no image
Fluctuating interface with a pinning potential

Pranjić, Daniel

Universität Stuttgart, Stuttgart, 2019 (mastersthesis)

icm

[BibTex]

[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
Controlling pattern formation in the confined Schnakenberg model

Beyer, David Bernhard

Universität Stuttgart, Stuttgart, 2019 (mastersthesis)

icm

[BibTex]

[BibTex]


no image
Interfaces in fluids of ionic liquid crystals

Bartsch, H.

Universität Stuttgart, Stuttgart, 2019 (phdthesis)

icm

link (url) DOI [BibTex]

link (url) DOI [BibTex]


no image
Actively Learning Dynamical Systems with Gaussian Processes

Buisson-Fenet, M.

Mines ParisTech, PSL 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]

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]


no image
Diffusion im Zentrifugalpotential

Totikos, Vangelis

Universität Stuttgart, Stuttgart, 2016 (mastersthesis)

icm

[BibTex]

[BibTex]


{Statische und dynamische Magnetisierungseigenschaften nanoskaliger \"Uberstrukturen}
Statische und dynamische Magnetisierungseigenschaften nanoskaliger Überstrukturen

Gräfe, J.

Universität Stuttgart, Stuttgart (und Cuvillier Verlag, Göttingen), 2016 (phdthesis)

mms

[BibTex]

[BibTex]


no image
Electromagnetic radiation in complex environments: Many body systems and background medium

Müller, Boris

Universität Stuttgart, Stuttgart, 2016 (mastersthesis)

icm

[BibTex]

[BibTex]


no image
Interface-controlled phenomena in nanomaterials

Mittemeijer, Eric J.; Wang, Zumin

2016 (mpi_year_book)

Abstract
Nanosized material systems characteristically exhibit an excessively high internal interface density. A series of previously unknown phenomena in nanomaterials have been disclosed that are fundamentally caused by the presence of interfaces. Thus anomalously large and small lattice parameters in nanocrystalline metals, quantum stress oscillations in growing nanofilms, and extraordinary atomic mobility at ultralow temperatures have been observed and explained. The attained understanding for these new phenomena can lead to new, sophisticated applications of nanomaterials in advanced technologies.

link (url) [BibTex]

link (url) [BibTex]


no image
Theory of enantiomer separation by external fields

Gehrmann, Christian

Universität Stuttgart, Stuttgart, 2016 (mastersthesis)

icm

[BibTex]

[BibTex]


no image
Robots learn how to see

Geiger, A.

2016 (mpi_year_book)

Abstract
Autonomous vehicles and intelligent service robots could soon contribute to making our lives more pleasant and secure. However, for autonomous operation such systems first need to learn the perception process itself. This involves measuring distances and motions, detecting objects and interpreting the threedimensional world as a whole. While humans perceive their environment with seemingly little efforts, computers first need to be trained for these tasks. Our research is concerned with developing mathematical models which allow computers to robustly perceive their environment.

link (url) DOI [BibTex]


no image
General properties of ionic complex fluids

Bier, M.

Universität Stuttgart, Stuttgart, 2016 (phdthesis)

icm

[BibTex]

[BibTex]


no image
Wedge wetting by an electrolyte solution

Mu\ssotter, M.

Universität Stuttgart, Stuttgart, 2016 (mastersthesis)

icm

[BibTex]

[BibTex]


no image
Gepinnte Bahnmomente in magnetischen Heterostrukturen

Audehm, P.

Universität Stuttgart, Stuttgart (und Cuvillier Verlag, Göttingen), 2016 (phdthesis)

mms

[BibTex]

[BibTex]


no image
Austauschgekoppelte Moden in magnetischen Vortexstrukturen

Dieterle, G.

Universität Stuttgart, Stuttgart, 2016 (phdthesis)

mms

[BibTex]

[BibTex]


no image
Density matrix calculations for the ultrafast demagnetization after femtosecond laser pulses

Weng, Weikai

Universität Stuttgart, Stuttgart, 2016 (mastersthesis)

mms

[BibTex]

[BibTex]


no image
Deep Learning for Diabetic Retinopathy Diagnostics

Balles, Lukas

Heidelberg University, 2016 (mastersthesis)

[BibTex]

[BibTex]


no image
Helium und Hydrogen Isotope Adsorption and Separation in Metal-Organic Frameworks

Zaiser, Ingrid

Universität Stuttgart, Stuttgart (und Cuvillier Verlag, Göttingen), 2016 (phdthesis)

mms

[BibTex]

[BibTex]

2013


no image
Camera-specific Image Denoising

Schober, M.

Eberhard Karls Universität Tübingen, Germany, October 2013 (diplomathesis)

ei pn

PDF [BibTex]

2013


PDF [BibTex]


Statistics on Manifolds with Applications to Modeling Shape Deformations
Statistics on Manifolds with Applications to Modeling Shape Deformations

Freifeld, O.

Brown University, August 2013 (phdthesis)

Abstract
Statistical models of non-rigid deformable shape have wide application in many fi elds, including computer vision, computer graphics, and biometry. We show that shape deformations are well represented through nonlinear manifolds that are also matrix Lie groups. These pattern-theoretic representations lead to several advantages over other alternatives, including a principled measure of shape dissimilarity and a natural way to compose deformations. Moreover, they enable building models using statistics on manifolds. Consequently, such models are superior to those based on Euclidean representations. We demonstrate this by modeling 2D and 3D human body shape. Shape deformations are only one example of manifold-valued data. More generally, in many computer-vision and machine-learning problems, nonlinear manifold representations arise naturally and provide a powerful alternative to Euclidean representations. Statistics is traditionally concerned with data in a Euclidean space, relying on the linear structure and the distances associated with such a space; this renders it inappropriate for nonlinear spaces. Statistics can, however, be generalized to nonlinear manifolds. Moreover, by respecting the underlying geometry, the statistical models result in not only more e ffective analysis but also consistent synthesis. We go beyond previous work on statistics on manifolds by showing how, even on these curved spaces, problems related to modeling a class from scarce data can be dealt with by leveraging information from related classes residing in di fferent regions of the space. We show the usefulness of our approach with 3D shape deformations. To summarize our main contributions: 1) We de fine a new 2D articulated model -- more expressive than traditional ones -- of deformable human shape that factors body-shape, pose, and camera variations. Its high realism is obtained from training data generated from a detailed 3D model. 2) We defi ne a new manifold-based representation of 3D shape deformations that yields statistical deformable-template models that are better than the current state-of-the- art. 3) We generalize a transfer learning idea from Euclidean spaces to Riemannian manifolds. This work demonstrates the value of modeling manifold-valued data and their statistics explicitly on the manifold. Specifi cally, the methods here provide new tools for shape analysis.

ps

pdf Project Page [BibTex]


no image
Modelling and Learning Approaches to Image Denoising

Burger, HC.

Eberhard Karls Universität Tübingen, Germany, 2013 (phdthesis)

ei

[BibTex]

[BibTex]


no image
Perceiving Systems – Computers that see

Gehler, P. V.

2013 (mpi_year_book)

Abstract
Our research goal is to define in a mathematical precise way how visual perception works. We want to describe how intelligent systems understand images. To this end we study probabilistic models and statistical learning. Encoding prior knowledge about the world is complemented with automatic learning from training data. One aspect is being able to identify physical factors in images, such as lighting, geometry, and materials. Furthermore we want to automatically recognize and give names to objects and persons in images and understand the scene as a whole.

link (url) [BibTex]


no image
Linear mixed models for genome-wide association studies

Lippert, C.

University of Tübingen, Germany, 2013 (phdthesis)

ei

[BibTex]

[BibTex]


no image
Brownian motion of optically trapped ellipsoids

Dibak, Manuel

Universität Stuttgart, Stuttgart, 2013 (mastersthesis)

icm

[BibTex]

[BibTex]


no image
Being small, being smart

Liu, Na

2013 (mpi_year_book)

Abstract
Metallic nanostructures feature plasmonic resonances which spatially confine light on the nanometer scale. In the ultimate limit of a single nanostructure, the electromagnetic field can be strongly concentrated in a volume of only a few hundred nm3 or less. We utilize such plasmonic focusing for hydrogen detection at the single particle level, which avoids any inhomogeneous broadening and statistical effects that would occur in sensors based on nanoparticle ensembles. This concept paves the road towards the observation of single catalytic processes in nanoreactors.

link (url) [BibTex]

link (url) [BibTex]


no image
Phase behavior of colloidal suspensions with critical solvents

Mohry, T. F.

Universität Stuttgart, Stuttgart, 2013 (phdthesis)

icm

link (url) [BibTex]

link (url) [BibTex]


no image
Modeling and Learning Complex Motor Tasks: A case study on Robot Table Tennis

Mülling, K.

Technical University Darmstadt, Germany, 2013 (phdthesis)

ei

[BibTex]

[BibTex]