My research focuses on computing and understanding motion in the world from video. In generic scenes I study optical flow (the 2D image motion) and how it relates to physical properties of the world including 3D shape, material, illumination, and motion. I also develop new methods to capture natural, complex, human and animal motion for applications in computer vision, animation, and neuroscience.

I am interested in computer vision and machine learning with a focus on 3D scene understanding, parsing and reconstruction. During my Ph.D. I have developed probabilistic models for 3D traffic scene understanding from movable platforms.

I am personal assistant to Prof. Stefan Schaal and provide administrative support fo the Autonomous Motion Department.

Back from parental leave, I am happy to continue working as a personal assistant to Professor Bernhard Schölkopf and to the lab members of his Empirial Inference Department, together with my colleague Diana Rebmann.

My research focuses on perception for autonomous robotic manipulation and grasping. I believe that these methods have to be goal-directed, real-time and multi-modal such that they can provide meaningful feedback for execution and learning.

I am a research group leader at the Bernstein Center for Computational Neuroscience and the Max Planck Instiute for Intelligent Systems in Tübingen. Before, I was postdoctoral researcher at ETH Zurich, temporary Professor at TU Darmstadt, and Junior Research Group Leader at the MPI for Informatik. I did my PhD studies in the Empirical Inference group at the MPI for Biological Cybernetics. My main research focus lies on visual scene understanding. I want to enable computers to reason about the physical world around us. This requires models that can infer about the semantic, as well as the physical properties of visual data. I believe that both problems should be addressed jointly. I have broad interest in computer vision and machine learning topics with a focus on statistical models and inference techniques. Applications range from material and reflectance separation, to detection and pose estimation.

Sebastian Trimpe is a Senior Research Scientist and Group Leader at the Max Planck Institute for Intelligent Systems. He leads the Intelligent Control Systems group within the Autonomous Motion Department.

My main interests include computer vision and machine learning. I focus on depth estimation and 3D reconstruction, with a mix between applied and more theoretical research.

Research on Active Cooperative SLAM

I am currently a Ph.D. student in Computer Science at University of Southern California (USC), advised by Prof. Hao Li. My research interests are in capturing, modeling and understanding human face / body.  From September 2016, I started this research internship in the Perceiving Systems dept. at the Max Planck Institute for Intelligent Systems. I'm mentored by Dr. Javier Romero. 

Advisor: Andreas Geiger

I am a doctoral student in the Department of Electrical Engineering at the Indian Institute of Science - Bangalore, advising by Dr Soma Biswas, Assistant Professor. My research interests are in computer vision and pattern recognition with applications to low resolution face recognition.

Enthusiastic Machine learning developer with major research area in deep learning and computer vision, currently focussing on learning meaningful features using unsupervised deep learning algorithms.

From January 2017 to July 2017 I am a master student in the BCI group. My master thesis will be about the development and evaluation of a revolutionary low cost BCI device which should in the future allow remote data acquisition all over the world. In September and October 2016 I was composing an essay with the topic "Barriers and Opportunities of user-centered BCI development - A review of current development and recommendations for further initiatives". Since April 2016 I am employed as a research assistant for data acquisition in the BCI group. My tasks include the conduction of EEG sessions with ALS patients.

I am doing a six-month internship in the field of Brain-Control Rehabilitation Robots for stroke patients, in the Brain Computer Interface Group, under the supervision of Dr. Grosse-Wentrup .

Advisor: Jeannette Bohg

I am an intern for Summer 2017, working on optical flow algorithm on mobile and embedded systems. I am currently a masters student in the School of Computing, Informatics and Design System Engineering (CIDSE) at Arizona State University, USA. My research interests are in computer vision, graphics and mobile systems.

My main research interests lie in Bayesian sensor fusion and optimization-based state estimation. The core application focus of my research is vision-based perception in Robotics. I have worked with several ground robots in the recent past. Currently, I am focusing on aerial robots and active perception in multiple aerial vehicle systems.

I work with computer vision researchers to coordinate, schedule and run human subjects trials involving body shape and motion analysis at the Perceiving Systems Department. To collect data we use several computer vision technologies, including our unique 3D and 4D body scanners and our new 4D face scanner.

Advisor: Philipp Hennig

Advisor: Philipp Hennig

Advisor: Sebastian Trimpe

Advisor: Andreas Geiger

My research is in the area of Computer Vision and Machine Learning. Currently, I am working on problems related to estimation of 3D motion fields from stereo image sequences.

I am a technician working one half each in the groups of Bernhard Schölkopf and Heinrich Bülthoff. In the Bülthoff Department I support the experiments of Isabelle Bülthoff who is working on face recognition.

My research focus and interest is in the area of 3D computer vision and computer graphics. I am especially interested in non-rigid shape analysis, statistical modelling of various kinds of shapes, and the analysis of motion data.

Advisor: Jan Peters

I have a broad interest in machine learning and applied mathematics. I am particularly interested in how the field of causal inference can benefit traditional machine learning problems such as transfer learning and reinforcement learning.

My interests are non-rigid registration of images and video, Bayesian estimation, and their robotic and biomedical applications.

Advisor: Andreas Geiger

I'm working on "Efficient Invariant Deep Models for Computer Vision" in cooperation with Bosch.

Advisor: Sebastian Trimpe
Jeannette Bohg

Advisor: Sebastian Trimpe

Advisor: Peter Vincent Gehler

I am doing a PhD in the field of machine learning and robotics. I work in the empirical inference department and my supervisor is Jan Peters. Our aim is to build reinforcement learning algorithms that can learn control policies for complex robotics tasks such as robot table tennis. For that we need to include as much prior knowledge as possible into our models, since experiments on the real robot are usually expensive. My interest are mostly in machine learning, reinforcement learning and Bayesian inference. But I also like algorithms and math, and before coming to the MPI I used to participate in competitions on these topics.

PhD student in Cambridge-Tuebingen program with primary research focus in deep learning, reinforcement learning, approximate inference, and robotics.

Advisor: Andreas Geiger

I am interested in estimating 3D scene representations from multi-view video sequences. In particular, I focus on combining semantic segmentation, object detection and classification with 3D reconstruction using efficient inference methods.

Brain-Computer Interface for ALS Patients

Yinghao Huang is a PhD candidate at Max Planck Institute for Intelligent Systems, supervised by Director Michael J. Black. His research interests fall in the areas of Machine Learning, Computer Vision and Computer Graphics. More specifically, he focuses on the topics of Human Body Modelling, 3D Human Shape and Pose Estimation, and other related things.

Advisor: Peter Vincent Gehler

I am working on leveraging machine learning techniques for better inference in computer vision applications. The main research question is how to make use of learning techniques such as deep neural networks and random forests for inference in structured prediction frameworks.

Advisor: Andreas Geiger

Perception is a fundamental part of intelligence since perception is necessary to acquire knowledge and knowledge is necessary to understand perception. Therefore computer vision is one of the most important aspects in the realization of intelligent systems. My interest of research lies in computer vision and the combination with machine learning which, to my mind, will enable the realization of intelligent systems. Currently, I am working on optical flow and how to incorporate high-level information to alleviate this ill-posed problem.

Advisor: Jeannette Bohg

I am a PhD student at Empirical Inference Department, Max Planck Institute for Intelligent Systems and Werner Siemens Imaging Center, UKT, Tuebingen. My work focuses on the assessment of tumor heterogeneity using multi-modality (PET/MR) imaging for personalized cancer therapies. I am also very interested in applying statistical methods on the data originating from multi-modal and heterogeneous sources. Before moving to Germany, i obtained my masters degree in systems engineering from Politecnico Di Milano, Italy.

I coordinate our department's research trials. We collect data on human body shape and pose. This includes 3D and 4D body scans, face scans, anthropometric measurements, Motion Capture, and further (experimental) technologies. I recruit participants, schedule, manage appointments, create protocols of poses and movements and gain data according to our scientists' needs. Also, I process the data and take care of data security. Besides that, I am responsible for organising lab tours for visitors of our department.

Advisor: Philipp Hennig

PhD student

My research concerns learning models of perception and production of non-verbal communicative behavior. Such models can be used to create richer human-robot and human-avatar interaction, for medical diagnosis systems, and for contextual synthesis of different kinds of human behaviors, e.g., guiding synthesis of hand motion from body motion.

Advisor: Jeannette Bohg

Advisor: Jan Peters

I'm an intern for summer 2017 working on relating speech and facial movement.

Advisor: Peter Vincent Gehler

How can autonomous perception discover high-dimensional patterns in recorded data from our environment? I am approaching this question by working on structured computer vision tasks, such as Human Pose Estimation. I hope that insights from this area will improve our data analysis systems, so that they can assist us in better understanding our environment.

My work focuses on improving human body shape and pose estimation from different sensor based systems. I help develop tools and methods for capturing and processing data from depth/ToF sensors and mocap-like systems. I am also involved in developing tools to implement research projects into existing computer graphics and animation pipelines.

Advisor: Philipp Hennig