Home  ·   Publications  ·   More


Zhongang Cai   蔡中昂


Hi there! I am a Ph.D. student at MMLab@NTU, advised by Prof. Ziwei Liu and Prof. Chen Change Loy. My research interests include point clouds and virtual humans. Concurrently, I am also a Senior Algorithm Researcher at SenseTime Research. My responsibility includes building systems and algorithms that perceive, reconstruct and generate humans.

Google Scholar GitHub Twitter

News

[2023-01] I gave an invited talk on HuMMan and GTA-Human in MPI.

[2023-01] Release of HuMMan v1.0: Reconstruction Subset.

[2022-10] We are organizing ECCV 2022 SenseHuman Workshop.

[2022-09] 1 paper accepted to NeurIPS (Datasets and Benchmarks Track) 2022.

[2022-07] 2 papers accepted to ECCV 2022 (1 oral and 1 poster).

[2022-05] 1 papers accepted to SIGGRAPH 2022 (journal-track).

[2022-03] 3 papers accepted to CVPR 2022 (1 oral and 2 posters).

[2021-12] We have released MMHuman3D: 3D Human Parametric Model Toolbox and Benchmark

[2021-07] We are hosting MVP Challenge.

[2021-06] We are organizing ICCV 2021 SenseHuman Workshop.

My Three Favorite Works [Full List]


HuMMan: Multi-Modal 4D Human Dataset for Versatile Sensing and Modeling

Zhongang Cai*, Daxuan Ren*, Ailing Zeng*, Zhengyu Lin*, Tao Yu*, Wenjia Wang*, Xiangyu Fan, Yang Gao, Yifan Yu, Liang Pan, Fangzhou Hong, Mingyuan Zhang, Chen Change Loy, Lei Yang, Ziwei Liu.
European Conference on Computer Vision (ECCV), 2022 (Oral)

PDF Project Page Code Dataset Demo






Benchmarking and Analyzing 3D Human Pose and Shape Estimation Beyond Algorithms

Hui En Pang, Zhongang Cai, Lei Yang, Tianwei Zhang, Ziwei Liu.
NeurIPS (Datasets and Benchmarks Track), 2022

PDF Code




Playing for 3D Human Recovery

Zhongang Cai*, Mingyuan Zhang*, Jiawei Ren*, Chen Wei, Daxuan Ren, Jiatong Li, Zhengyu Lin, Haiyu Zhao, Shuai Yi, Lei Yang, Chen Change Loy, Ziwei Liu.
arXiv Preprint, 2021

PDF Project Page Code Dataset







On-Going Projects


MMHuman3D is an open source PyTorch-based codebase for the use of 3D human parametric models. It is a part of the OpenMMLab project.
    - Reproducing popular methods with a modular framework
    - Supporting various datasets with a unified data convention
    - Versatile visualization toolbox

Watch Fork Star