Publications | Max Planck Institute for Intelligent Systems

365 results (View BibTeX file of all listed publications)

2023

Efficient Sampling from Differentiable Matrix Elements

Technical University of Munich, Germany, September 2023 (mastersthesis)

2023

ei Kofler, A. Efficient Sampling from Differentiable Matrix Elements Technical University of Munich, Germany, September 2023 (mastersthesis)

[BibTex]

Intrinsic complexity and mechanisms of expressivity of cortical neurons

Spieler, A. M.

University of Tübingen, Germany, March 2023 (mastersthesis)

[BibTex]

ei Spieler, A. M. Intrinsic complexity and mechanisms of expressivity of cortical neurons University of Tübingen, Germany, March 2023 (mastersthesis)

[BibTex]

Towards Generative Machine Teaching

Qui, Z.

Technical University of Munich, Germany, February 2023 (mastersthesis)

[BibTex]

ei Qui, Z. Towards Generative Machine Teaching Technical University of Munich, Germany, February 2023 (mastersthesis)

[BibTex]

Generation and Quantification of Spin in Robot Table Tennis

Dittrich, A.

University of Stuttgart, Germany, January 2023 (mastersthesis)

[BibTex]

ei Dittrich, A. Generation and Quantification of Spin in Robot Table Tennis University of Stuttgart, Germany, January 2023 (mastersthesis)

[BibTex]

2022

Reconstructing Expressive 3D Humans from RGB Images

Choutas, V.

ETH Zurich, Max Planck Institute for Intelligent Systems and ETH Zurich, December 2022 (thesis)

Abstract

To interact with our environment, we need to adapt our body posture and grasp objects with our hands. During a conversation our facial expressions and hand gestures convey important non-verbal cues about our emotional state and intentions towards our fellow speakers. Thus, modeling and capturing 3D full-body shape and pose, hand articulation and facial expressions are necessary to create realistic human avatars for augmented and virtual reality. This is a complex task, due to the large number of degrees of freedom for articulation, body shape variance, occlusions from objects and self-occlusions from body parts, e.g. crossing our hands, and subject appearance. The community has thus far relied on expensive and cumbersome equipment, such as multi-view cameras or motion capture markers, to capture the 3D human body. While this approach is effective, it is limited to a small number of subjects and indoor scenarios. Using monocular RGB cameras would greatly simplify the avatar creation process, thanks to their lower cost and ease of use. These advantages come at a price though, since RGB capture methods need to deal with occlusions, perspective ambiguity and large variations in subject appearance, in addition to all the challenges posed by full-body capture. In an attempt to simplify the problem, researchers generally adopt a divide-and-conquer strategy, estimating the body, face and hands with distinct methods using part-specific datasets and benchmarks. However, the hands and face constrain the body and vice-versa, e.g. the position of the wrist depends on the elbow, shoulder, etc.; the divide-and-conquer approach can not utilize this constraint. In this thesis, we aim to reconstruct the full 3D human body, using only readily accessible monocular RGB images. In a first step, we introduce a parametric 3D body model, called SMPL-X, that can represent full-body shape and pose, hand articulation and facial expression. Next, we present an iterative optimization method, named SMPLify-X, that fits SMPL-X to 2D image keypoints. While SMPLify-X can produce plausible results if the 2D observations are sufficiently reliable, it is slow and susceptible to initialization. To overcome these limitations, we introduce ExPose, a neural network regressor, that predicts SMPL-X parameters from an image using body-driven attention, i.e. by zooming in on the hands and face, after predicting the body. From the zoomed-in part images, dedicated part networks predict the hand and face parameters. ExPose combines the independent body, hand, and face estimates by trusting them equally. This approach though does not fully exploit the correlation between parts and fails in the presence of challenges such as occlusion or motion blur. Thus, we need a better mechanism to aggregate information from the full body and part images. PIXIE uses neural networks called moderators that learn to fuse information from these two image sets before predicting the final part parameters. Overall, the addition of the hands and face leads to noticeably more natural and expressive reconstructions. Creating high fidelity avatars from RGB images requires accurate estimation of 3D body shape. Although existing methods are effective at predicting body pose, they struggle with body shape. We identify the lack of proper training data as the cause. To overcome this obstacle, we propose to collect internet images from fashion models websites, together with anthropometric measurements. At the same time, we ask human annotators to rate images and meshes according to a pre-defined set of linguistic attributes. We then define mappings between measurements, linguistic shape attributes and 3D body shape. Equipped with these mappings, we train a neural network regressor, SHAPY, that predicts accurate 3D body shapes from a single RGB image. We observe that existing 3D shape benchmarks lack subject variety and/or ground-truth shape. Thus, we introduce a new benchmark, Human Bodies in the Wild (HBW), which contains images of humans and their corresponding 3D ground-truth body shape. SHAPY shows how we can overcome the lack of in-the-wild images with 3D shape annotations through easy-to-obtain anthropometric measurements and linguistic shape attributes. Regressors that estimate 3D model parameters are robust and accurate, but often fail to tightly fit the observations. Optimization-based approaches tightly fit the data, by minimizing an energy function composed of a data term that penalizes deviations from the observations and priors that encode our knowledge of the problem. Finding the balance between these terms and implementing a performant version of the solver is a time-consuming and non-trivial task. Machine-learned continuous optimizers combine the benefits of both regression and optimization approaches. They learn the priors directly from data, avoiding the need for hand-crafted heuristics and loss term balancing, and benefit from optimized neural network frameworks for fast inference. Inspired from the classic Levenberg-Marquardt algorithm, we propose a neural optimizer that outperforms classic optimization, regression and hybrid optimization-regression approaches. Our proposed update rule uses a weighted combination of gradient descent and a network-predicted update. To show the versatility of the proposed method, we apply it on three other problems, namely full body estimation from (i) 2D keypoints, (ii) head and hand location from a head-mounted device and (iii) face tracking from dense 2D landmarks. Our method can easily be applied to new model fitting problems and offers a competitive alternative to well-tuned traditional model fitting pipelines, both in terms of accuracy and speed. To summarize, we propose a new and richer representation of the human body, SMPL-X, that is able to jointly model the 3D human body pose and shape, facial expressions and hand articulation. We propose methods, SMPLify-X, ExPose and PIXIE that estimate SMPL-X parameters from monocular RGB images, progressively improving the accuracy and realism of the predictions. To further improve reconstruction fidelity, we demonstrate how we can use easy-to-collect internet data and human annotations to overcome the lack of 3D shape data and train a model, SHAPY, that predicts accurate 3D body shape from a single RGB image. Finally, we propose a flexible learnable update rule for parametric human model fitting that outperforms both classic optimization and neural network approaches. This approach is easily applicable to a variety of problems, unlocking new applications in AR/VR scenarios.

pdf [BibTex]

2022

ps Choutas, V. Reconstructing Expressive 3D Humans from RGB Images ETH Zurich, Max Planck Institute for Intelligent Systems and ETH Zurich, December 2022 (thesis)

pdf [BibTex]

Investigating Independent Mechanisms in Neural Networks

Liang, W.

Université Paris-Saclay, France, October 2022 (mastersthesis)

[BibTex]

ei Liang, W. Investigating Independent Mechanisms in Neural Networks Université Paris-Saclay, France, October 2022 (mastersthesis)

[BibTex]

Modeling subgroup differences in fMRI data: disentangling subgroup-specific responses from shared ones

Keidar, D.

ETH Zurich, Switzerland, October 2022 (mastersthesis)

[BibTex]

ei Keidar, D. Modeling subgroup differences in fMRI data: disentangling subgroup-specific responses from shared ones ETH Zurich, Switzerland, October 2022 (mastersthesis)

[BibTex]

Causality, causal digital twins, and their applications

Schölkopf, B.

Machine Learning for Science: Bridging Data-Driven and Mechanistic Modelling (Dagstuhl Seminar 22382), (Editors: Berens, Philipp and Cranmer, Kyle and Lawrence, Neil D. and von Luxburg, Ulrike and Montgomery, Jessica), September 2022 (talk)

link (url) DOI [BibTex]

ei Schölkopf, B. Causality, causal digital twins, and their applications Machine Learning for Science: Bridging Data-Driven and Mechanistic Modelling (Dagstuhl Seminar 22382), (Editors: Berens, Philipp and Cranmer, Kyle and Lawrence, Neil D. and von Luxburg, Ulrike and Montgomery, Jessica), September 2022 (talk)

link (url) DOI [BibTex]

Multi-Target Multi-Object Manipulation using Relational Deep Reinforcement Learning

Feil, M.

Technnical University Munich, Germany, September 2022 (mastersthesis)

[BibTex]

ei Feil, M. Multi-Target Multi-Object Manipulation using Relational Deep Reinforcement Learning Technnical University Munich, Germany, September 2022 (mastersthesis)

[BibTex]

Independent Mechanism Analysis for High Dimensions

Sliwa, J.

University of Tübingen, Germany, September 2022, (Graduate Training Centre of Neuroscience) (mastersthesis)

[BibTex]

ei Sliwa, J. Independent Mechanism Analysis for High Dimensions University of Tübingen, Germany, September 2022, (Graduate Training Centre of Neuroscience) (mastersthesis)

[BibTex]

On the Adversarial Robustness of Causal Algorithmic Recourse

Dominguez-Olmedo, R.

University of Tübingen, Germany, August 2022 (mastersthesis)

[BibTex]

ei Dominguez-Olmedo, R. On the Adversarial Robustness of Causal Algorithmic Recourse University of Tübingen, Germany, August 2022 (mastersthesis)

[BibTex]

Independent Mechanism Analysis in High-Dimensional Observation Spaces

Ghosh, S.

ETH Zurich, Switzerland, June 2022 (mastersthesis)

[BibTex]

ei Ghosh, S. Independent Mechanism Analysis in High-Dimensional Observation Spaces ETH Zurich, Switzerland, June 2022 (mastersthesis)

[BibTex]

Voltage dependent investigations on the spin polarization of layered heterostructues

Miller, M.

Universität Stuttgart, Stuttgart, 2022 (mastersthesis)

mms

[BibTex]

mms Miller, M. Voltage dependent investigations on the spin polarization of layered heterostructues Universität Stuttgart, Stuttgart, 2022 (mastersthesis)

[BibTex]

2021

Learning Neural Causal Models with Active Interventions

Scherrer, N.

ETH Zurich, Switzerland, November 2021 (mastersthesis)

[BibTex]

2021

ei Scherrer, N. Learning Neural Causal Models with Active Interventions ETH Zurich, Switzerland, November 2021 (mastersthesis)

[BibTex]

HealthGen: Conditional Generation of Realistic Medical Time Series with Informative Missingness

Bing, S.

ETH Zurich, Switzerland, October 2021 (mastersthesis)

[BibTex]

ei Bing, S. HealthGen: Conditional Generation of Realistic Medical Time Series with Informative Missingness ETH Zurich, Switzerland, October 2021 (mastersthesis)

[BibTex]

Study of the Interventional Consistency of Autoencoders

Lanzillotta, G.

ETH Zurich, Switzerland, October 2021 (mastersthesis)

[BibTex]

ei Lanzillotta, G. Study of the Interventional Consistency of Autoencoders ETH Zurich, Switzerland, October 2021 (mastersthesis)

[BibTex]

Physically Plausible Tracking & Reconstruction of Dynamic Objects

Strecke, M., Stückler, J.

KIT Science Week Scientific Conference & DGR-Days 2021, October 2021 (talk)

[BibTex]

ev Strecke, M., Stückler, J. Physically Plausible Tracking & Reconstruction of Dynamic Objects KIT Science Week Scientific Conference & DGR-Days 2021, October 2021 (talk)

[BibTex]

Training with Few to Manipulate Many. On OOD generalization in relational reinforcement learning

Mambelli, D.

ETH Zurich, Switzerland, October 2021 (mastersthesis)

[BibTex]

ei Mambelli, D. Training with Few to Manipulate Many. On OOD generalization in relational reinforcement learning ETH Zurich, Switzerland, October 2021 (mastersthesis)

[BibTex]

Improving Human Decision-Making by Discovering Efficient Strategies for Hierarchical Planning

Heindrich, L., Consul, S., Stojcheski, J., Lieder, F.

Tübingen, Germany, The first edition of Life Improvement Science Conference, June 2021 (talk) Accepted

Abstract

The discovery of decision strategies is an essential part of creating effective cognitive tutors that teach planning and decision-making skills to humans. In the context of bounded rationality, this requires weighing the benefits of different planning operations compared to their computational costs. For small decision problems, it has already been shown that near-optimal decision strategies can be discovered automatically and that the discovered strategies can be taught to humans to increase their performance. Unfortunately, these near-optimal strategy discovery algorithms have not been able to scale well to larger problems due to their computational complexity. In this talk, we will present recent work at the Rationality Enhancement Group to overcome the computational bottleneck of existing strategy discovery algorithms. Our approach makes use of the hierarchical structure of human behavior by decomposing sequential decision problems into two sub-problems: setting a goal and planning how to achieve it. An additional metacontroller component is introduced to switch the current goal when it becomes beneficial. The hierarchical decomposition enables us to discover near-optimal strategies for human planning in larger and more complex tasks than previously possible. We then show in online experiments that teaching the discovered strategies to humans improves their performance in complex sequential decision-making tasks.

Project Page [BibTex]

re Heindrich, L., Consul, S., Stojcheski, J., Lieder, F. Improving Human Decision-Making by Discovering Efficient Strategies for Hierarchical Planning Tübingen, Germany, The first edition of Life Improvement Science Conference, June 2021 (talk) Accepted

Project Page [BibTex]

Robotic Surgery Training in AR: Multimodal Record and Replay

Krauthausen, F.

pages: 1-147, University of Stuttgart, Stuttgart, May 2021, Study Program in Software Engineering (mastersthesis)

[BibTex]

hi Krauthausen, F. Robotic Surgery Training in AR: Multimodal Record and Replay pages: 1-147, University of Stuttgart, Stuttgart, May 2021, Study Program in Software Engineering (mastersthesis)

[BibTex]

Direct detection of spin Hall effect induced torques in platinum/ferromagnetic bilayer systems

Alten, F.

Universität Stuttgart, Stuttgart, January 2021 (mastersthesis)

mms

[BibTex]

mms Alten, F. Direct detection of spin Hall effect induced torques in platinum/ferromagnetic bilayer systems Universität Stuttgart, Stuttgart, January 2021 (mastersthesis)

[BibTex]

Reinforcement Learning Algorithms: Analysis and Applications

Belousov, B., H., A., Klink, P., Parisi, S., Peters, J.

883, Studies in Computational Intelligence, Springer International Publishing, 2021 (book)

DOI [BibTex]

ei Belousov, B., H., A., Klink, P., Parisi, S., Peters, J. Reinforcement Learning Algorithms: Analysis and Applications 883, Studies in Computational Intelligence, Springer International Publishing, 2021 (book)

DOI [BibTex]

Community detection in heterogeneously attributed networks

Zottino, N.

Politecnico di Torino, 2021 (mastersthesis)

pio

link (url) [BibTex]

pio Zottino, N. Community detection in heterogeneously attributed networks Politecnico di Torino, 2021 (mastersthesis)

link (url) [BibTex]

2020

Voltage dependent interfacial magnetism in multilayer systems

Nacke, R.

Universität Stuttgart, Stuttgart, December 2020 (thesis)

mms

[BibTex]

2020

mms Nacke, R. Voltage dependent interfacial magnetism in multilayer systems Universität Stuttgart, Stuttgart, December 2020 (thesis)

[BibTex]

Hydromagnonics: Manipulation of magnonic systems with hydrogen

Sauter, R.

Universität Stuttgart, Stuttgart, December 2020 (mastersthesis)

mms

[BibTex]

mms Sauter, R. Hydromagnonics: Manipulation of magnonic systems with hydrogen Universität Stuttgart, Stuttgart, December 2020 (mastersthesis)

[BibTex]

A Robotic Manipulation Benchmark for Causal Structure and Transfer Learning

Ahmed, O.

ETH Zurich, Switzerland, October 2020 (mastersthesis)

[BibTex]

ei Ahmed, O. A Robotic Manipulation Benchmark for Causal Structure and Transfer Learning ETH Zurich, Switzerland, October 2020 (mastersthesis)

[BibTex]

A Comprehensive Benchmark Evaluation of Synthetic Data Generation for Biomedical Imaging

DuMont Schütte, A.

ETH Zurich, Switzerland, October 2020 (mastersthesis)

[BibTex]

ei DuMont Schütte, A. A Comprehensive Benchmark Evaluation of Synthetic Data Generation for Biomedical Imaging ETH Zurich, Switzerland, October 2020 (mastersthesis)

[BibTex]

Deep learning for the parameter estimation of tight-binding Hamiltonians

Cacioppo, A.

University of Roma, La Sapienza, Italy, May 2020 (mastersthesis)

[BibTex]

ei Cacioppo, A. Deep learning for the parameter estimation of tight-binding Hamiltonians University of Roma, La Sapienza, Italy, May 2020 (mastersthesis)

[BibTex]

Beyond Basins of Attraction: Quantifying Robustness of Natural Dynamics

Heim, S., Badri-Spröwitz, A.

May 2020 (talk)

dlg

Presentation [BibTex]

dlg Heim, S., Badri-Spröwitz, A. Beyond Basins of Attraction: Quantifying Robustness of Natural Dynamics May 2020 (talk)

Presentation [BibTex]

Learning Algorithms, Invariances, and the Real World

Zecevic, M.

Technical University of Darmstadt, Germany, April 2020 (mastersthesis)

[BibTex]

ei Zecevic, M. Learning Algorithms, Invariances, and the Real World Technical University of Darmstadt, Germany, April 2020 (mastersthesis)

[BibTex]

Interaction of hydrogen isotopes with flexible metal-organic frameworks

Bondorf, L.

Universität Stuttgart, Stuttgart, February 2020 (mastersthesis)

mms

[BibTex]

mms Bondorf, L. Interaction of hydrogen isotopes with flexible metal-organic frameworks Universität Stuttgart, Stuttgart, February 2020 (mastersthesis)

[BibTex]

Developing new methods for routing and optimal transport on networks

Lonardi, A.

Università degli studi di Padova, 2020 (mastersthesis)

pio

pdf [BibTex]

pio Lonardi, A. Developing new methods for routing and optimal transport on networks Università degli studi di Padova, 2020 (mastersthesis)

pdf [BibTex]

Edge-Disjoint Path Problem on Stochastic Block Models through Message Passing

Lorenzo Ferretti

Sapienza Università di Roma, 2020 (mastersthesis)

pio

[BibTex]

pio Lorenzo Ferretti Edge-Disjoint Path Problem on Stochastic Block Models through Message Passing Sapienza Università di Roma, 2020 (mastersthesis)

[BibTex]

Colloidal particles supporting urase activity

Baldauf, A.

Univ. of Stuttgart, 2020 (mastersthesis)

[BibTex]

pf Baldauf, A. Colloidal particles supporting urase activity Univ. of Stuttgart, 2020 (mastersthesis)

[BibTex]

Computer Vision for Autonomous Vehicles: Problems, Datasets and State-of-the-Art

Janai, J., Güney, F., Behl, A., Geiger, A.

Arxiv, Foundations and Trends in Computer Graphics and Vision, 2020 (book)

Abstract

Recent years have witnessed enormous progress in AI-related fields such as computer vision, machine learning, and autonomous vehicles. As with any rapidly growing field, it becomes increasingly difficult to stay up-to-date or enter the field as a beginner. While several survey papers on particular sub-problems have appeared, no comprehensive survey on problems, datasets, and methods in computer vision for autonomous vehicles has been published. This monograph attempts to narrow this gap by providing a survey on the state-of-the-art datasets and techniques. Our survey includes both the historically most relevant literature as well as the current state of the art on several specific topics, including recognition, reconstruction, motion estimation, tracking, scene understanding, and end-to-end learning for autonomous driving. Towards this goal, we analyze the performance of the state of the art on several challenging benchmarking datasets, including KITTI, MOT, and Cityscapes. Besides, we discuss open problems and current research challenges. To ease accessibility and accommodate missing references, we also provide a website that allows navigating topics as well as methods and provides additional information.

avg

pdf Project Page link Project Page [BibTex]

avg Janai, J., Güney, F., Behl, A., Geiger, A. Computer Vision for Autonomous Vehicles: Problems, Datasets and State-of-the-Art Arxiv, Foundations and Trends in Computer Graphics and Vision, 2020 (book)

pdf Project Page link Project Page [BibTex]

Diffusion studies on biomolecules by NMR

Bochert, I.

Univ. of Stuttgart, 2020 (mastersthesis)

[BibTex]

pf Bochert, I. Diffusion studies on biomolecules by NMR Univ. of Stuttgart, 2020 (mastersthesis)

[BibTex]

2019

Multivariate coupling estimation between continuous signals and point processes

Safavi, S., Logothetis, N., Besserve, M.

Neural Information Processing Systems 2019 - Workshop on Learning with Temporal Point Processes, December 2019 (talk)

Talk video link (url) [BibTex]

2019

ei Safavi, S., Logothetis, N., Besserve, M. Multivariate coupling estimation between continuous signals and point processes Neural Information Processing Systems 2019 - Workshop on Learning with Temporal Point Processes, December 2019 (talk)

Talk video link (url) [BibTex]