Visual Computing and Artificial Intelligence

People

Director

Secretaries

Research Group Leaders

Postdoctoral Researchers

PhD Candidates

Youngchan Kim

Associated students

(IMPRS, co-advised with P. Slusallek (UdS/DFKI))

(IMPRS, co-advised with P. Slusallek (UdS/DFKI))

Student in Max-Planck-ETH-Center for Learning Systems, CLS, co-advised with Marc Pollfefeys

Student in Max-Planck-ETH-Center for Learning Systems, CLS, co-advised with Jan Eric Lenssen, Siyu Tang, Bernt Schiele

Research Engineer

Associated researchers

Current and former Master/Diplom/Bachelor Students and Supervised Theses

  • Hendrik Junkawitsch: EVA: Expressive Virtual Avatars from Muli-view Video (2025).
  • Basavaraj Rajenda Sunagad: Tedra: Text-based Editing of Dynamic and Photoreal Actors (2024).
  • Ashwat Shetty: Holoported Characters: Real-time Free-viewpoint Rendering of Humans from Spars RGB Cameras (2024).
  • Saurabh Panday: Outlier-Robust Multi-model Fitting on Quantum Hardware (2024).
  • Chengjangrong Peng: Semantics Guided Inverse Rendering with Global Illumination (2024).
  • Muhammad Ovais: Egocentric-driven Facial Avatars for Real-Time Telepresence (2024).
  • Christen Millerdurai: 3D Human Motion Capture from Egocentric Event Streams (2024).
  • Muhammad Hamza Mughal: Multi-Modal Modeling of Speech and Gesture in Multi-Person dialogue (2024).
  • Suhas Gopal: Separable Multi-view 3D Human Object Reconstruction (2024).
  • Amr Farghaly, Personality-aware Non-verbal Behaviour Generation in Dyadik Interactions (2024).
  • Pankhuri Vanjani : Multi-Modal Modeling of Speech and Gesture in Multi-Person dialogue (2023).
  • Kartik Teotia : HQ3D Avatar: High Quality Controllable 3D Head Avatar (2023).
  • Akshay Mundra: LiveHand: Real-time and Photorealistic Neural Hand Rendering (2023).
  • Amr Amer, Non-verbal Visual Human Behaviour Generation (2023).
  • Zhouyingcheng Liao,  Video-based Neural Character Skinning(2022).
  • Pramod Rao, VoRF: Volumetric Relightable Faces (2022).
  • Navami Kairanda, φ-SfT: Shape-from-Template with a Physics-Based Deformation Model (2022).
  • Erik Johnson,  Monocular Non-Rigid 4D Reconstruction using a Deformable Implicit Scene Model(2022).
  • André Jonas, 3D Tracking of Two Hands from an Event Camera (2021).
  • Maximilian Krahn, Joint Graph Matching and Graph Clustering (2021).
  • Mohit Mendiratta, Egocentric Videoconferencing (2021).
  • Jalees Nehvi, Differentiable Event Stream Simulator for Non-Rigid 3D Tracking (2021)
  • Vikramjit Sidhu, Neural Dense Non-Rigid Structure from Motion with Latent Space Constraints (2020).
  • Tarun Yenamandra, i3DMM: Deep Implicit Morphable 3D Head Model (2020).
  • Hyoseung Kang, Semidefinite Programming in Computer Vision with Lower-Rank Factorization (2019).
  • Zeeshan Khan Suri, A Low-Dimensional Deformation Model for Non-Rigid Shape Matching (2019).
  • Chitra Singh, Combined 3D Eye and Face Reconstruction using Monocular RGB Images (2019).
  • Hossein Hajipour, Weakly-supervised Surface Reconstruction Using Floating Radial Basis Functions (2018).
  • Mohammad Shafiei, Live Global Intrinsic Video (2018).
  • Marc Habermann, Template-based 3D reconstruction of non-rigid surfaces from 4K RGB video (2017).
  • Jianan Ma (co-advisor; main advisor Klaus Fischer (DFKI), Real-time Character Control.
  • Max Augustin, Data-Parallel Shading-based Refinement (2016).
  • Franziska Mueller: Real-time Hand Tracking (2015).
  • Mandana Eghbali, High-Quality facial performance capture with a Kinect camera (2013).
  • Daniyar Kurmankhoyayev (MPI Informatics/Saarland Univ.), Monocular pose capture with depth cameras using a Sums-of-Gaussians body model (2013).
  • Hamid Sarmadi (KTH Stockholm/MPI Informatics), Part detection for video-based motion capture (2013).
  • Elham Afsari Yeganeh (MPI Informatics/Saarland Univ.), Motion alignment of videos captured with a Kinect (2013).
  • Nadia Robertini (MPI Informatics/Saarland Univ.), Data-driven modeling with depth cameras (2013).
  • Ebad Pirmoradian (MPI Informatics/Saarland Univ.), Monocular performance capture via ToF cameras (2011).
  • Martin Simonowski, Hand Shape Recognition using a Time-of-Flight Camera: An Application to Sign Language (2011).
  • Alexander Martens, Data-driven Cloth Animation (2011).
  • Sebastian Schuon (TU Munich, MPI Informatics and Stanford University), Resolution Enhancement for 3D Time-of-Flight Cameras (2010).
  • Derek Chan (Stanford University), Real-time Upsampling of of Depth Camera Images (2009).
  • Sergey Levine (Stanford University), Body Language Animation Synthesis from Prosody (2009).
  • Jens Kerber, Cross-platform Adaptation of a Free-Viewpoint Viedeo Viewer (2004).
  • Edilson de Aguiar, Character Animation from a Motion Capture Database (2003).

Former Ph.D. Students

  • Linjie Lyu, PhD in VCAI department (graduated 2026 - thesis: Global Illumination in Inverse Rendering: From Probabilistic Reconstruction to Generative Editing), now CTO & Co-Founder of Bridge.
  • Gereon Fox, PhD in VCAI department (graduated 2025 - thesis: Learning and Exploiting Temporal Dependencies in the Synthesis and Analysis of Video Signals), now Research Engineer at Max Planck Institute for Informatics.
  • Jian Wang, PhD in VCAI department (graduated 2024 - thesis: Egocentric Motion Capture), now Research Scientist at Meta.
  • Soshi Shimada, PhD in VCAI department (graduated 2024 - thesis: Physically plausible 3D human motion capture and synthesis with interactions), now Research Scientist at Netflix.
  • Edith Tretschk, PhD in VCAI department (graduated 2024 - thesis: Representing and Reconstructing General Non-Rigid Objects with Neural Models), now at Meta Reality Labs Research.
  • Ikhsanul Habibie, PhD in VCAI department (graduated 2023 - thesis: Learning-based 3D human motion capture and animation).
  • Jiayi Wang, PhD in VCAI department (graduated 2023 - thesis: 3D Hand Reconstruction from Monocular Camera with Model-Based Priors), now at Bosch Research.
  • Marc Habermann, PhD in VCAI department (graduated 2021 - thesis: Real-time human performance capture and synthesis), now group leader in VCAI.
  • Ayush Tewari, PhD in VCAI department (graduated 2021 - thesis: Self-Supervised Reconstruction and Synthesis of Faces), now postdoc at MIT.
  • Franziska Mueller, PhD in GVV group (graduated 2020 - thesis: Real-time 3D Hand Reconstruction in Challenging Scenes from a Single Color or Depth Camera), now at Google.
  • Dushyant Mehta, PhD in GVV group (graduated 2020 - thesis: Real-time 3D Human Body Pose Estimation from Monocular RGB Input), now at Qualcomm.
  • Abhimitra Meka, PhD in GVV group (graduated 2020 - thesis: Live Inverse Rendering), now at Google.
  • Hyeongwoo Kim, PhD in GVV group (graduated 2019 - thesis: Learning-based Face Reconstruction and Editing), now at Imperial College London.
  • Nadia Robertini, PhD in GVV group (graduated 2019 - thesis: Model-based Human Performance Capture in Outdoor Scenes), now at Image Technologies Gmbh.
  • Pablo Garrido, PhD in GVV group (graduated 2017 - thesis: High-quality face capture, animation and editing from monocular video), postdioc at Technicolor, now Researcher at EPIC Research.
  • Srinath Sridhar, Co-supervised with Antti Oulasvirta, PhD in GVV group (graduated 2016 - thesis: Tracking Hands in Action for Gesture-based Computer Input), postdoc at Stanford University, starting as Assistant Professor at Brown University (Fall 2020).
  • Helge Rhodin, PhD in GVV group (graduated 2016 - thesis: From motion capture to interactive virtual worlds), postdoc at EPFL, now assistant professor at the Univ. of British Columbia
  • Ahmed Elhayek, PhD in GVV group (graduated 2015 - thesis: Marker-less motion capture in general scenes with sparse multi-camera setups), postdoc at DFKI, now asst. professor at University of Prince Mugrin, Saudia Arabia
  • Chenglei Wu, PhD student GVV group (graduated 2014 - thesis: Inverse Rendering for Scene Reconstruction in General Environments), postoc at ETH Zurich , now researcher at Facebook Reality Labs Pittsburgh
  • Miguel Granados, PhD student in GVV group (graduated 2013 - thesis: Advanced Editing Methods for Image and Video Sequences), postdoc in GVV group 2014, now at Magicleap
  • Thomas Helten, PhD student in GVV group (co-advised with Meinard Mueller, graduated 2013 - thesis: Processing and Tracking Human Motions Using Optical, Inertial, and Depth Sensors), now at Pixargus / GoalControl
  • Mohammed Shaheen (co-advised with Robert Strzodka, graduated 2013 - thesis: Cache based Optimization of Stencil Computations An Algorithmic Approach), now at IBM
  • Andreas Baak (co-advised wth Meinard Mueller, graduated 2012 - thesis: Retrieval-based Approaches for Tracking and Reconstructing Human Motions), now at BMW
  • Gernot Ziegler (MPII) - PhD at MPII (graduated 2010 - thesis: GPU Data Structures for Graphics and Vision), now at Nvidia
  • Carsten Stoll, PhD at MPII (graduated 2009 - thesis: Template Based Shape Processing,), formerly senior researcher in MPC-VCC, researcher at Weta Digital, co-founder of theCaptury, now at Oculus Research
  • Naveed Ahmed (MPII) - PhD at MPII (graduated 2009 - thesis: High-quality Dynamic Reflectance and Surface Reconstruction from Video), now professor at University of Sharjah, UAE
  • Edilson de Aguiar (MPII) - PhD at MPII (graduated 2008 - thesis: Animation and Performance Capture Using Digitized Models), formerly Disney Research Pittsburgh / Carnegie Mellon University - Assistant Professor, Federal University of Espirito Santo, Brazil

Alumni

  • Fangneng Zhan, Postdoctoral Fellow in VCAI Deparment (2022-2024), now Research Fellow affiliated with both Harvard University and MIT.
  • Diogo Luvizon, Postdoctoral Fellow in VCAI Department (2021-2024), now at Meta Reality Labs.
  • Mohamed Elgharib, Group Leader in VCAI Department (2018-2024), now AI Specialist at the ROSEN Group.
  • Xingang Pan, Postdoctoral Fellow in VCAI Department (2021-2023), now Asst. Professor at Nanyang Technological University.
  • Lingjie Liu, Lise Meitner Postdoctoral Fellow in GVV group/VCAI Department (2019-2023), now Asst. Professor at the University of Pennsylvania.
  • Mengyu Chu, Lise Meitner Postdoctoral Fellow in GVV group/VCAI Department (2020-2022), now Asst. Professor at Peking University.
  • Kripasindhu Sarkar, postdoc in VCAI group (2019-2022), now research scientist at Google.
  • Florian Bernard, postdoc in GVV group (2017-2020), now Professor at University of Bonn.
  • Weipeng Xu, postdoc in GVV group (2016-2019), now research scientist at Facebook Reality Labs.
  • Lan Xu, visiting PhD student from HKUST / Tsinghua University (one year, 2018-2019)
  • Yuxiao Zhou, visiting Bachelor student from Tsingua University, Bachelor thesis in GVV group (Feb-June 2019)
  • Lingjie Liu, visiting PhD student from University of Hong Kong (2018), now postdoc in GVV group
  • Michael Zollhöfer, postdoc in GVV group (2015-2017), now research scientist at Facebook Reality Labs.
  • Maxim Maximov, Research Immersion Lab student in GVV group (2016-2017)
  • Avishek Chatterjee, postdoc in GVV group (2016-2017), now Assistant Professor at Indian Institute of Technology Kharagpur
  • Dan Casas, postdoc in GVV group (2015-2016), now Asst. Professor at Universidad Rey Juan Carlos, Madrid
  • Christian Richardt, postdoc in GVV group (2014-2016), now lecturer at University of Bath
  • Levi Valgaerts, postdoc in GVV group (2011-2015), now at Apple, CH
  • Hamid Sarmadi, one year stay (2014) as researcher in GVV group
  • Nils Hasler, postdoc in GVV group, now CEO of the Captury
  • Michal Richter, research assistant in GVV group, now at the Captury
  • Kwang In Kim, postdoc in GVV group (2010-2013), formerly lecturer at Lancaster University, Senior Lecturer at University of Bath, now Professor at UNIST South Korea
  • James Tompkin, postdoc in GVV group (2012-2014), now Assistant Professor at Brown University, USA
  • Brojeshwar Bhowmick: visiting PhD student from Indian Institute of Technology (IIT), Delhi
  • Kiran Varanasi: postdoc in GVV group, later at Technicolor R&D and DFKI, now professor at HTW Leipzig
  • Rajvi Shah: visiting PhD student from Center for Visual Information Technology, IIIT Hyderabad
  • Thomas Neumann: visiting PhD student from HTW Dresden / TU Braunschweig
  • Gaurav Bharaj - Research Engineer 7/2010-8/2012, now PhD student at Harvard
  • Guannan Li - visiting PhD student (7/2011-1/2012) from Tsinghua University
  • Yebin Liu (MPII) - postdoc in GVV, now associate professor at Tsinghua University, Beijing
  • James Tompkin, visiting PhD student from University College London (2010 / 2011)
  • Dina Khattab - visiting PhD student from IIIT Hyderabad, 2010
  • Yan Cui - Hiwi 2009 - now at DFKI
  • Feng Xu visiting PhD student from Tsinghua University Beijing (2010/2011), now assistant professor at Tsinghua University
  • Savil Srivastava (Stanford) - Bachelor student
  • Young Min Kim (Stanford)
  • Derek Chan, MSc student, Stanford, now at Amazon
  • Varun Ganapathi, PhD student, Stanford, now at Google
  • Sebastian Schuon (Stanford), MSc student, Stanford, co-founder of Stylight