Our research is at the intersection of computer vision, computer graphics and machine learning--we develop computational algorithms to efficiently digitize people and train machines to perceive people from visual data.
Current computer vision algorithms can detect people in images or estimate 2D keypoints to a remarkable accuracy. However, people are far more complex–-we effortlessly sense other people's emotional state based on facial expressions and body movements, or we make guesses about people's preferences based on what clothing they wear. Our goal is to build virtual humans that look, move and eventually think like real ones.
News
Emmy Noether starting grant!
November 2018
Gerard Pons-Moll has been awarded an Emmy Noether grant. The grant, called like the group "Real Virtual Humans" (RVHu), conists of 1.6 Million euros to conduct research at the interesction of vision, graphics and learning with special focus on analyzing and digitizing humans.
Senior researcher
November 2018
Gerard Pons-Moll has been offically appointed Senior Researcher at Max Planck for Informatics and Saarland Informatics Campus.
3 papers accepted at 3DV 2018!
1 Paper won the best student paper award!
September 2018
Pdfs and videos available!
-Neural Body Fitting: Unifying Deep Learning and Model Based Human Pose and Shape Estimation
3DV Best Student Paper Award
-Detailed Human Avatars from Monocular Video
-Single-Shot Multi-Person 3D Pose Estimation From Monocular RGB
1 paper at ECCV'18
September 2018
Recovering Accurate 3D Human Pose in The Wild Using IMUs and a Moving Camera
New dataset with ground truth 3D poses in the wild! Download
We have released the first (and most challenging) dataset of natural scenes with multiple people with accurate 3D pose and shape! The RGB video includes scenes like taking the bus, walking on the city, shoping, sports, etc.
PeopleCap'18 workshop at ECCV'18
September 14th 2018
Gerard Pons-Moll and Jonathan Taylor will organize the second edition of PeopleCap.
The workshop will bring together researchers in the fields of 3D human modelling, reconstruction and tracking. Submission deadline is July 20th
Science article about our CVPR'18 paper
April 13th 2018
One of our CVPR papers has been covered in the Science magazine.
We developed a method to create a 3D avatar from a few seconds of video footage. See the Paper.
Latest Publications
ReTiCaM: Real-time Human Performance Capture from Monocular Video
in arXiv2018, 2019.
Accepted with minor revisions
Fashion is Taking Shape: Understanding Clothing Preference Based on Body Shape From Online Sources
in IEEE Winter Conference on Applications of Computer Vision (WACV 2019), 2019.
Deep Inertial Poser Learning to Reconstruct Human Pose from SparseInertial Measurements in Real Time
in ACM Transactions on Graphics, (Proc. SIGGRAPH Asia), vol. 37, no. 6, 185:1-185:15 2018.