I am a Research Scientist at Epic Games, specializing in the development next generation digital humans.
I earned my PhD in Computer Graphics and Computer Vision from the Max-Planck Institute for Informatics with Prof. Christian Theobalt. I also lead a group on Optical Performance Capture at the Max-Planck Center for Visual Computing and Communication and spent a year as visiting researacher at Weta Digital. I cofounded The Captury, a company focused on real-time markerless motion capture, and then joined Facebook Reality Labs to work on full body virtual humans, before joining Epic in 2020.
My research interests span a wide range of topics from computer graphics, geometric modeling, animation, and computer vision. My primary goal is to advance the technology and tools to create and control fully photorealistic and believable digital human avatars.
Projects
At
Epic Games I developed the ML model driving Unreal Engine's
ML Deformer plugin that can be used to create a high-fidelity next-generation character with deformations driven by full muscle, flesh, and cloth simulation running in real-time.
Momentum
At Facebook/Oculus Research I developed the
Momentum library for human kinematics and numerical optimization that was used to prototype markerless motion capture algorithms and was used for early versions of the Oculus VR headset upper body tracking.
Publications
(in reverse chronological order)
2024
-
HUMOS: Human Motion Model Conditioned on Body Shape
Shashank Tripathi, Omid Taheri, Christoph Lassner, Michael J. Black, Daniel Holden, and Carsten Stoll
In ECCV, 2024
-
EPOCH: Jointly Estimating the 3D Pose of Cameras and Humans
Nicola Garau, Giulia Martinelli, Niccolo Bisagno, Denis Tome, and Carsten Stoll
In ECCV T-CAP Workshop, 2024
-
fNeRF: High Quality Radiance Fields from Practical Cameras
In arxiv, 2024
-
PhisaNet: Phonetically Informed Speech Animation Network
Salvador Medina, Sarah L. Taylor,
Carsten Stoll, Gareth Edwards, Alex Hauptmann, Shinji Watanabe, and
Iain Matthews In ICASSP, 2024
2023
-
Personalized 3D Human Pose and Shape Refinement
In IEEE/CVF ICCVW, 2023
2022
-
Speech Driven Tongue Animation
Salvador Medina, Denis Tomè,
Carsten Stoll, Mark Tiede, Kevin Munhall, Alex Hauptmann, and
Iain Matthews In IEEE/CVF CVPR, 2022
2021
-
ANR: Articulated Neural Rendering for Virtual Avatars
Amit Raj, Julian Tanke, James Hays, Minh Vo, Carsten Stoll, and Christoph Lassner
In IEEE CVPR, 2021
2020
-
TexMesh: Reconstructing Detailed Human Texture and Geometry from RGB-D Video
Tiancheng Zhi, Christoph Lassner, Tony Tung, Carsten Stoll, Srinivasa G. Narasimhan, and Minh Vo
ECCV, 2020
-
PatchNets: Patch-Based Generalizable Deep Implicit 3D Shape Representations
Edgar Tretschk, Ayush Tewari, Vladislav Golyanik, Michael Zollhöfer,
Carsten Stoll, and
Christian Theobalt In ECCV, 2020
2015
-
Outdoor Human Motion Capture by Simultaneous Optimization of Pose and Camera Parameters
Eurographics, 2015
2013
-
Capturing Relightable Human Performances under General Uncontrolled Illumination
Guannan Li, Chenglei Wu,
Carsten Stoll, Yebin Liu, Kiran Varanasi, Qionghai Dai, and
Christian Theobalt Eurographics, 2013
-
Markerless Motion Capture of Multiple Characters Using Multiview Image Segmentation
IEEE PAMI, 2013
-
On-set performance capture of multiple actors with a stereo camera
SIGGRPAH Asia, 2013
2012
-
Coherent Spatiotemporal Filtering, Upsampling and Rendering of RGBZ Videos
Eurographics, 2012
-
Spatio-temporal motion tracking with unsynchronized cameras
In IEEE CVPR, 2012
-
Feature-Based Multi-video Synchronization with Subframe Accuracy
In DAGM, 2012
2011
-
Video-based characters: creating new human performances from a multi-view video database
SIGGRAPH Asia, 2011
-
Markerless motion capture of interacting characters using multi-view image segmentation
In , 2011
-
Fast articulated motion tracking using a sums of Gaussians body model
In ICCV, 2011
2010
-
Video-based reconstruction of animatable human characters
SIGGRAPH Asia, 2010
-
Joint Estimation of Motion, Structure and Geometry from Stereo Sequences
Levi Valgaerts, Andrés Bruhn, Henning Zimmer, Joachim Weickert,
Carsten Stoll, and
Christian Theobalt In ECCV, 2010
2009
-
Template based shape processing
Carsten Stoll
Saarland University, 2009
-
Estimating body shape of dressed humans
Nils Hasler,
Carsten Stoll, Bodo Rosenhahn, Thorsten Thormählen, and
Hans-Peter Seidel Shape Modeling International, 2009
-
-
Motion capture using joint skeleton tracking and surface estimation
In IEEE (CVPR), 2009
2008
-
Performance capture from sparse multi-view video
ACM SIGGRAPH, 2008
2007
-
Marker-less Deformable Mesh Tracking for Human Shape and Motion Capture
In IEEE (CVPR), 2007
-
A Volumetric Approach to Interactive Shape Editing
In Technical Report, 2007
-
Rapid Animation of Laser-scanned Humans
In IEEE VR, 2007
-
Geodesics guided constrained texture deformation
In Pacific Graphics, 2007
2006
-
BSP Shapes
In Shape Modeling and Applications, 2006
-
Incremental Raycasting of Piecewise Quadratic Surfaces on the GPU
In Symposium on Interactive Raytracing, 2006
-
Template Deformation for Point Cloud Fitting
In Point Based Graphics@SIGGRAPH, 2006
2005
-
Visualization with stylized line primitives
In IEEE Vis, 2005
2003
-
Direction Fields over Point-Sampled Geometry
Marc Alexa, Tobias Klug, and Carsten Stoll
In WSCG, 2003