Jinnan Chen

I'm currently a Ph.D. candidate at NUS School of Computing, supervised by Prof Gim Hee Lee. I received my B.E. degree from Wuhan University and MEng degree from Nanyang Technology University with a GPA of 5.0/5.0. During my master's study, I was supervised by Prof Jiang Xudong and Dr Qian Zheng.

Currently, my research interests are mainly in Computer Vision and Generative Models, including 3D Generation/Reconstruction/Animation (Mesh & 3DGS & Rigging/Skinning), Multimodal Video Generation (AR & Diffusion) and Unified Models (Understanding & Generation). I did research internship at Bytedance AI Lab, Tencent Games and Hedra Labs.

News

Publications

Auto-Connect: Connectivity-Preserving RigFormer with Direct Preference Optimization. [arXiv] [page]
Jingfeng Guo*, Jian Liu*, Jinnan Chen†, Shiwei Mao, Changrong Hu, Puhua Jiang, Junlin Yu, Jing Xu, Qi Liu†, Lixin Xu, Zhuo Chen, Chunchao Guo († Indicates Corresponding Author)
Annual Conference on Neural Information Processing Systems (NeurIPS) 2025

MAR-3D: Progressive Masked Auto-regressor for High-Resolution 3D Generation. [arXiv] [page] [code]
Jinnan Chen, Lingting Zhu, Zeyu Hu, Shengju Qian, Yugang Chen, Xin Wang, Gim Hee Lee
IEEE Conference on Computer Vision and Pattern Recognition（CVPR）2025 Highlight

Reconstructing Close Human Interaction with Appearance and Proxemics Reasoning. [arXiv] [page] [code]
Buzhen Huang, Chen Li, Chongyang Xu, Dongyue Lu, Jinnan Chen, Yangang Wang, Gim Hee Lee
IEEE Conference on Computer Vision and Pattern Recognition（CVPR）2025

Generalizable Human Gaussians from Single-View Image. [arXiv] [page] [code]
Jinnan Chen, Chen Li, Jianfeng Zhang, Lingting Zhu, Buzhen Huang, Hanlin Chen, Gim Hee Lee
The International Conference on Learning Representations（ICLR）2025

Large Images are Gaussians: High-quality Large Image Representation with Levels of 2D Gaussian Splatting. [arXiv] [code]
Lingting Zhu, Guying Lin, Jinnan Chen, Xinjie Zhang, Zhenchao Jin, Zhao Wang, Lequan Yu
The Association for the Advancement of Artificial Intelligence (AAAI) 2025

MuMA: 3D PBR Texturing via Multi-Channel Multi-View Generation and Agentic Post-Processing. [arXiv]
Lingting Zhu, Jingrui Ye, Runze Zhang, Zeyu Hu, Yingda Yin, Lanjiong Li, Jinnan Chen, Shengju Qian, Xin Wang, Qingmin Liao, Lequan Yu
Arxiv 2025

Forge4D: Feed-Forward 4D Human Reconstruction and Interpolation from Uncalibrated Sparse Videos. [arXiv] [Project Page]
Yingdong Hu*, Yisheng He*†, Jinnan Chen, Weihao Yuan, Kejie Qiu, Zehong Lin, Siyu Zhu, Zilong Dong, Jun Zhang
Arxiv 2025

DiHuR: Diffusion-Guided Generalizable Human Reconstruction. [arXiv]
Jinnan Chen, Chen Li, Gim Hee Lee
IEEE/CVF Winter Conference (WACV) 2025

Weakly-supervised 3D Pose Transfer with Keypoints. [arXiv] [page] [code]
Jinnan Chen, Chen Li, Gim Hee Lee
IEEE International Conference on Computer Vision (ICCV) 2023

Single image reflection removal with absorption effect. [paper] [code]
Qian Zheng, Boxin Shi, Jinnan Chen, Xudong Jiang, Ling-Yu Duan, Alex C. Kot
IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2021

Feature distillation with guided adversarial contrastive learning. [arXiv]
Tao Bai, Jinnan Chen, Jun Zhao, Bihan Wen, Xudong Jiang, Alex Kot
Arxiv 2020

What does plate glass reveal about camera calibration? [paper] [code]
Qian Zheng, Jinnan Chen, Zhan Lu, Boxin Shi, Xudong Jiang, Kim-Hui Yap, Ling-Yu Duan, Alex C. Kot
IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2020

Teaching

Academic Services (Reviewer)