Zhong Li(李众)

Senior Staff Research Scientist @ Innopeak Technology

Short Bio

I'm currently a senior staff research scientist at Innopeak Technology focusing on next-generation mobile AR/VR R&D. My research interests are in the Vision and Graphics related fields. More specifically, 2D/3D human body/face modeling and understanding, novel view synthesis, image-based rendering, and relighting. Before that, I obtained my Ph.D. degree in Computer Science from the University of Delaware, Newark, DE, USA. I worked on 3D non-rigid dynamic human shape reconstruction and completion, Dynamic mesh sequences compression, and human semantic segmentation.

Education

NEWS

  • We are consistently seeking highly motivated Ph.D. interns on various AR/VR topics including but not limit to 2D/3D human body/face modeling and understanding, novel view synthesis, image-based rendering, and relighting. Drop me an email if interested.

Selected Publications

Full-Vome 3D Fluid Flow Reconstruction with Light Field PIV

Yuqi Ding, Zhong Li, Zhang Chen, Yu Ji, Jingyi Yu, Jinwei Ye

IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) , 2023.

[Project Page][Paper(PDF)]

NeRFPlayer: A Streamable Dynamic Scene Representation with Decomposed Neural Radiance Fields.

Liangchen Song, Anpei Chen, Zhong Li, Zhang Chen, Lele Chen, Junsong Yuan, Yi Xu, and Andreas Geiger.

IEEE Conference on Virtual Reality and 3D User Interface(IEEE VR),2023

Special Issue on IEEE Transactions on Visualization & Computer Graphics (TVCG) , 2023.

[Paper(PDF)] [Project Page]

NeuLF: Efficient Novel View Synthesis with Neural 4D Light Field

Zhong Li, Liangchen Song, Celong Liu, Junsong Yuan and Yi Xu

Eurographics Symposium on Rendering (EGSR), 2022.

[Paper(PDF)] [Project Page][Video]

Real-Time Lighting Estimation for Augmented Reality via Differentiable Screen-Space Rendering

Liu, Celong, Lingyu Wang, Zhong Li, Shuxue Quan, and Yi Xu.

IEEE Transactions on Visualization & Computer Graphics (TVCG) , 2022.

[Paper(PDF)]

Robustfusion: Robust volumetric performance reconstruction under human-object interactions from monocular rgbd stream


Su, Zhuo and Xu, Lan and Zhong, Dawei and Li, Zhong and Deng, Fan and Quan, Shuxue and Fang, Lu


IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) , 2022.

[Paper(PDF)]

PoP-Net: Pose over Parts Network for Multi-Person 3D Pose Estimation from a Depth Image

Yuliang Guo, Zhong Li, Zekun Li, Xiangyu Du, Shuxue Quan and Yi Xu

IEEE Winter Conference on Computer Vision (WACV), 2022

[Paper(PDF)] [Datasets]

Learning Kinematic Formulas from Multiple View Videos

Liangchen Song, Sheng Liu, Celong Liu, Zhong Li, Yuqi Ding, Yi Xu, and Junsong Yuan,

ACM International Conf. on Multimedia (ACM MM), 2021

[Paper(PDF)]

3D Fluid Flow Reconstruction Using Compact Light Field PIV

Zhong Li, Yu Ji, Jingyi Yu, Jinwei Ye

European Conference on Computer Vision (ECCV), 2020

[Paper(PDF)][Video]

Talking-head Generation with Rhythmic Head Motion

Lele Chen, Guofeng Cui, Celong Liu, Zhong Li, Ziyi Kou, Yi Xu, and Chenliang Xu

European Conference on Computer Vision (ECCV), 2020

[Paper(PDF)][Video]

Structure from Motion on XSlit Cameras

Wei Yang, Yingliang Zhang, Jinwei Ye, Yu Ji, Zhong Li, Mingyuan Zhou, and Jingyi Yu.

IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) 2019.

[Paper(PDF)]

3D Human Avatar Digitization from a Single Image

Zhong Li , Lele Chen, Celong Liu, , Yu Gao, Yuanzhou Ha , Chenliang Xu , Shuxue Quan, Yi Xu

Computer & Graphics (C & G), 2021.

ACM SIGGRAPH VRCAI (VRCAI), 2019.(Best paper award) .

[Paper(PDF)][Journal Extension]


Pose2Body: Pose-Guided Human Parts Segmentation.

Zhong Li, Xin Chen, Wangyiteng Zhou,Yingliang Zhang and Jingyi Yu.

IEEE Conference on Multimedia and Expo (ICME), 2019. (Oral Presentation)

[Paper(PDF)][Supplemental Materials]

4D Human Body Correspondences from Panoramic Depth Maps

Zhong Li, Minye Wu, Wangyiteng Zhou and Jingyi Yu.

IEEE Conference on Computer Vision and Pattern Recognition (CVPR),2018

[Paper(PDF)] [Video] [Press1] [Press2]

Robust 3D Human Motion Reconstruction Via Dynamic Template Construction

Zhong Li, Yu Ji, Wei Yang, Jinwei Ye and Jingyi Yu.

International Conference on 3D Vision (3DV), 2017. (Spotlight Oral Presentation)

[Paper(PDF)] [Video] [Data]

The Light Field 3D Scanner

Yingliang Zhang, Zhong Li, Wei Yang, Peihong Yu, Haiting Lin, Jingyi Yu

IEEE International Conference on Computational Photography (ICCP), 2017. (Oral Presentation)

[Paper(PDF)]

Professional Activity

Conference reviewer: CVPR 2021/2022/2023. ICCV 2021. ECCV 2022. AAAI 2020/2021, IJCAI 2023, ISMAR2022, IEEE VR 2023

Journal reviewer: Computer & Graphics, Machine Vision & Applications, The Visual Computer Journal(TVCJ), IEEE Access

US PATENT

Teaching

CISC 106: GEN COMPUTER SCIEN FOR ENGNR (Graduate TA 15 fall)

CISC 220: DATA STRUCTURE(Graduate TA 16 spring)