Digital Human AI Research (DAIR)

Welcome to the homepage of NVIDIA’s Digital Human AI Research (DAIR) group, led by Umar Iqbal. We are part of the Learning and Perception Research (LPR) organization. The team aims to improve and democratize the creation of photorealistic and dynamic 3D digital humans that appear realistic and move naturally when animated. We are particularly interested in:

Digital Human Generation and Animation
Neural Rendering and Reconstruction
Human-centric AI

News

Feb 2025 - SimAvatar accepted to CVPR 2025!

Feb 2025 - The DAIR website goes live!!

Members

Jiefeng Li

Computer Vision, Machine Learning, Generative AI

Umar Iqbal

Team Leader

Xueting Li

Computer Vision, 3D Vision

Ye Yuan

3D Vision, Embodied AI, Reinforcement Learning

Current and Past Interns

Marcel Buhler, ETH Zurich, 2024-2025
Jinkun Cao, Carnegie Mellon University (CMU), 2024-2025
Yangyi Huang, Zhejiang University, 2024
Bradley Kim, Seoul National University, 2024-2025
Jiefeng Li, Shanghai Jiao Tong University (SJTU), 2023-2024

Publications

Zhenyu Jiang, Yuqi Xie, Jinhan Li, Ye Yuan, Yifeng Zhu, Yuke Zhu

November 2024 Conference on Robot Learning (CoRL)

Harmon: Whole-Body Motion Generation of Humanoid Robots from Language Descriptions

arXiv Website

Jifeng Li, Ye Yuan, Davis Rempe, Haotian Zhang, Pavlo Molchanov, Cewu Lu, Jan Kautz, Umar Iqbal

September 2024 European Conference on Computer Vision (ECCV)

COIN: Control-Inpainting Diffusion Prior for Human and Camera Motion Estimation

arXiv Website

Yufeng Zheng, Xueting Li, Koki Nagano, Sifei Liu, Karsten Kreis, Otmar Hilliges, Shalini De Mello

June 2024 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

Dream-in-4D: A Unified Approach for Text- and Image-guided 4D Scene Generation

arXiv Website

Ye Yuan, Xueting Li, Yangyi Huang, Shalini De Mello, Koki Nagano, Jan Kautz, Umar Iqbal

June 2024 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Highlight

GAvatar: Animatable 3D Gaussian Avatars with Implicit Mesh Learning

arXiv Website

Mathis Petrovich, Or Litany, Umar Iqbal, Michael J. Black, Gül Varol, Xue Bin Peng, Davis Rempe

June 2024 CVPR Workshop on Human Motion Generation (HuMoGen)

Multi-Track Timeline Control for Text-Driven 3D Human Motion Generation

arXiv

Alex Trevithick, Matthew Chan, Towaki Takikawa, Umar Iqbal, Shalini De Mello, Manmohan Chandraker, Ravi Ramamoorthi, Koki Nagano

June 2024 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

Rendering Every Pixel for High-Fidelity Geometry in 3D GANs

arXiv

Yang Fu, Shalini De Mello, Xueting Li, Amey Kulkarni, Jan Kautz, Xiaolong Wang, Sifei Liu

May 2024 International Conference on Learning Representations (ICLR)

3D Reconstruction with Generalizable Neural Fields using Scene Priors

arXiv Website

Muhammed Kocabas, Ye Yuan, Pavlo Molchanov, Yunrong Guo, Michael Black, Otmar Hilliges, Jan Kautz, Umar Iqbal

March 2024 International Conference on 3D Vision (3DV)
Spotlight

PACE: Human and Camera Motion Estimation from in-the-wild Videos

arXiv

Xueting Li, Shalini De Mello, Sifei Liu, Koki Nagano, Umar Iqbal, Jan Kautz

December 2023 Advances in Neural Information Processing Systems (NeurIPS)

Generalizable One-shot Neural Head Avatar

arXiv

Jingbo Wang, Ye Yuan, Zhengyi Luo, Kevin Xie, Dahua Lin, Umar Iqbal, Sanja Fidler, Sameh Khamis

October 2023 IEEE International Conference on Computer Vision (ICCV)

Learning Human Dynamics in Autonomous Driving Scenarios

pdf

See all publications