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.
For all enquiries please contact:
Jessi Endress
Administrative Assistant
+ 49 7071 29 70803
jessica.endress@uni-tuebingen.de
News
Best Paper Honourable Mention at ECCV2022!!
Oct 2022
Congratulations to Garvita Tiwari, Dimitrije Antic, Jan Eric Lenssen, Nikolaos Sarafianos, Tony Tung and Gerard Pons-Moll for receiving the Best Paper Honorable Mention at ECCV'22 for the paper Pose-NDF: Modeling Human Pose Manifolds with Neural Distance Fields. 3 paper awards were given out of 6773 submissions.
EG-Italy Best Thesis Award!
Oct 2022
Congratulations for Riccardo Marin for winning the EG-Italy Best Thesis Award! His PhD thesis "Merging, extending and learning representations for 3D shape matching" exploits, extends, and proposes representations to establish correspondences in the non-rigid domain.
ECCV 2022 Outstanding Reviewers
Oct 2022
Bharat Lal Bhatnagar and Keyang Zhou are Outstanding Reviewers at ECCV22.
Best Paper Honourable Mention at 3DV2022!
Sep 2022
Our paper "Any-Shot GIN: Generalizing Implicit Networks for Reconstructing Novel Classes" has been selected as the Best Paper Honourable Mention at 3DV2022. Congratulations to all the authors!
7 Papers(2 Orals) accepted at ECCV2022!
July 2022
Topics are: 1) Single image reconstruction of humans and objects, 2) Contact-driven human motion synthesis, 3) Learning a pose manifold(Oral), 4) Re-targeting human motion to non-human characters, 5) Human-hand interaction, 6) Learning based model fitting and 7) Weakly supervised 3D instance segmentation(Oral). Congratulations students and collaborators!
Code, data and papers will be available here.
Riccardo Marin will join as Postdoctoral Researcher
May 2022
Riccardo Marin will join our group from July 2022 as a Postdoctoral researcher and is supported by Humboldt Fellowship.
CVPR 2022 Outstanding Reviewers
May 2022
Bharat Lal Bhatnagar, Garvita Tiwari, Julian Chibane, Ilya Petrov and Riccardo Marin are Outstanding Reviewers at CVPR22.
Facebook / Meta Research Fellowship Award
Feb 2022
Congratulations to Julian Chibane to be selected for the prestigious Facebook / Meta research fellowship award for his work on capture and synthesis of 3D scenes and humans! (37 selected out of 2300 applications).
Julian is greatful for his advisor Gerard Pons-Moll and collaborators!
Julian's fellowship profile: here.
Winners of CVPR SHARP'21 Challenges
June 2021
Congratulations to Julian Chibane and Gerard Pons-Moll for winning both 3D completion tracks of the CVPR'21 SHARP challenge on 3D shape recovery from partial textured 3D scans.
We won with IF-Nets (Chibane et al. CVPR'20) to complete geometry and texture (Chibane et al. ECCV-Workshop'20) plus an effective trick to retain even more detail of the input. In our experience, the model is easy to use, and works really well for a wide variety of 3D completion and reconstruction tasks. Code available here.
HPS has been shortlisted for best paper award at CVPR 2021!
June 2021
Only 32 papers out of 7000+ submissions have been selected as award candidates. Congratulations! Data and code are now available here!
Big News! The group is moving to Tuebingen
March 2021
Gerard Pons-Moll accepted a W3 professorship at the University of Tübingen at the department of Computer Science. The group will focus on learning, vision and graphics, with focus on capturing and synthesizing human and object shape apperance, as well as learning digital humans which can move and interact with the 3D world. More infos here.
4 Papers (1 oral) accepted at #CVPR2021!
March 2021
Pdfs, data and code will be available soon! here!
Topics are:
1) HPS: Capturing and self-localizing humans in large 3D scenes with IMUs and a head mounted camera (Oral).
2) Stereo Radiance Fields: generalizing NeRF to multiple scenes using classical stereo principles.
3) SMPLicit: An implicit based representation of people in layered clothing.
4) D-Nerf: generalizing NeRF to dynamic scenes.
Congratulations students and collaborators!2 Papers accepted at NeurIPS (1 Oral, 1 Poster)
August 2020
Papers are:
-1) LoopReg: Self-supervised Learning of Implicit Surface Correspondences, Pose and Shape for 3D Human Mesh Registration
-2) Neural Unsigned Distance Fields for Implicit Function Learning
Congrats to the team, and thanks to the reviewers for helping us in improving our papers!Code, data and papers will be available here.
Winners of all ECCV SHARP'20 Challenges
August 2020
Congratulations to Julian Chibane and Gerard Pons-Moll for winning all tracks of the ECCV'20 SHARP challenge on 3D shape recovery from partial textured 3D scans.
We extended IF-Nets (Chibane et al. CVPR'20) to complete geometry and texture (Chibane et al. ECCV-Workshop'20). In our experience, the model is easy to use, and works really well for a wide variety of 3D completion and reconstruction tasks. Code available here.
5 Papers (2 orals, 3 posters) accepted at #ECCV2020!
July 2020
Pdfs, data and code will be available soon! here!
Topics are: 1) Combining implicit functions and meshes for reconstruction, 2) A model of cloth sizing, 3) Unsupervised disentanglement of shape and pose from meshes, 4) A human implicit function parameterized by pose (NASA) and 5) Monocular 3D object detection in driving scenes. Congratulations students and collaborators!
CVPR20 Best Student Paper Honorable Mention!
June 2020
Congrats to collaborators, and thanks to the reviewers for useful feedback, and the awards committee for selecting our paper among many others worthy of the prize--we are honored.
3DPW Challenge and Workshop at ECCV 2020 featured on the front-page of computer vision news
June 2020
Gerard Pons-Moll, Angjoo Kanazawa, Michael Black and Aymen Mir talk about challenges in perceiving people in 3D, see the interview. Thanks Ralph Ansarouth!
Deadline is approaching, participate!: 3DPW Challenge.
5 Papers (2 orals, 3 posters) accepted at #CVPR2020!
February 2020
Pdfs, data and code are available here!
Congratulations to all collaborators!3DPW Challenge and Workshop at ECCV 2020.
February 2020
Gerard Pons-Moll will organize the first 3DPW Challenge and Workshop at ECCV 2020 together with Angjoo Kanazawa, Michael Black and Aymen Mir.
The aim of the workshop and challenge is to establish a benchmark to quantiatively evaluate 3D pose and shape human reconstruction methods in the wild using the 3DPW dataset.
Area Chair CVPR 2021 and 3DV 2020.
February 2020
Gerard Pons-Moll will serve as Area Chair for CVPR 2021
He will also serve as Area Chair for 3DV 2020
Area Chair ECCV 2020 and service.
2020
Gerard Pons-Moll will serve as Area Chair for ECCV 2020
He will also serve as Area Chair for Face and Gesture FG 2020
Selected as an Outstanding Reviewer of CVPR'19
German Pattern Recognition Award
September 2019
Gerard Pons-Moll has been awarded the 2019 German Pattern Recognition Award -- the highest prize awarded annualy to one researcher by the German Society of Computer Vision and Machine Learning.
Congrats to the group and collaborators!
3 papers accepted at ICCV 2019! 1 paper at 3DV'19
July 2019
Pdfs, data and code here!
-1) Multi-Garment Net: Learning to Dress 3D People from Images
-2) Tex2Shape: Detailed Full Human Body Geometry from a Single Image
-3) AMASS: Archive of Motion Capture as Surface Shapes
-4) 360-Degree Textures of People in Clothing from a Single Image
Congratulations to all co-authors!Google Faculty Research Award
February 2019
Gerard Pons-Moll received a Google Faculty Research Award.
We have open positions in our group: Job Offers3 papers accepted to CVPR 2019!
February 2019
Paper pdfs, videos and code coming soon!1) Learning to Reconstruct People in Clothing from a Single RGB Camera
2) SimulCap : Single-View Human Performance Capture with Cloth Simulation
3) In the Wild Human Pose Estimation using Explicit 2D Features and Intermediate 3D Representations
Congratulations to all co-authors!
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
Control-NeRF: Editable Feature Volumes for Scene Rendering and Manipulation
in Winter Conference on Applications of Computer Vision (WACV), 2023.
Adjoint Rigid Transform Network: Task-conditioned Alignment of 3D Shapes
in 2022 International Conference on 3D Vision (3DV), 2022.
Any-Shot GIN: Generalizing Implicit Networks for Reconstructing Novel Classes
in 2022 International Conference on 3D Vision (3DV), 2022.
Oral - Best Paper Honourable Mention