Jinnan Chen
California

Jinnan (Kenny) Chen

AI Engineer · Roblox Foundation AI

I received my Ph.D. from the National University of Singapore School of Computing in 2025, advised by Prof. Gim Hee Lee. Before that I received my B.E. from Wuhan University and my M.Eng. from Nanyang Technological University (GPA 5.0/5.0), where I was advised by Prof. Xudong Jiang and Dr. Zheng Qian.

My research centers on Computer Vision and Generative Models — including 3D Generation / Reconstruction / Animation (Mesh, 3DGS, Rigging & Skinning), Multimodal Video Generation (AR & Diffusion), and Unified Understanding–Generation Models. I'm currently an AI Engineer on Foundation AI at Roblox, and previously interned at Hedra Labs, Tencent Games, and ByteDance AI Lab.

I'm always open to research collaborations and discussions — feel free to reach out by email.

3D Generation Reconstruction Gaussian Splatting Rigging & Skinning Video Generation Unified Models

News

Apr 2026One paper accepted to TIP 2026.
Sep 2025One paper accepted to NeurIPS 2025.
May 2025Selected as Outstanding Reviewer at CVPR 2025.
Apr 2025MAR-3D selected as Highlight at CVPR 2025 (top 3% of submissions).
Feb 2025Two papers accepted to CVPR 2025.
Jan 2025One paper accepted to ICLR 2025.
Dec 2024One paper accepted to AAAI 2025.
Oct 2024One paper accepted to WACV 2025.
Jun 2023One paper accepted to ICCV 2023.
Feb 2021One paper accepted to CVPR 2021.
Feb 2020One paper accepted to CVPR 2020.

Selected Publications

3D Generation & Texturing
MuMA
MuMA: 3D PBR Texturing via Multi-Channel Multi-View Generation and Agentic Post-Processing
Lingting Zhu, Jingrui Ye, Runze Zhang, Zeyu Hu, Yingda Yin, Lanjiong Li, Jinnan Chen, Shengju Qian, Xin Wang, Qingmin Liao, Lequan Yu
IEEE Transactions on Image ProcessingTIP 2026
arXiv
UltraShape
UltraShape 1.0: High-Fidelity 3D Shape Generation via Scalable Geometric Refinement
Tanghui Jia, Dongyu Yan, Dehao Hao, Yang Li, Kaiyi Zhang, Xianyi He, Lanjiong Li, Jinnan Chen, Lutao Jiang, Qishen Yin, Long Quan, Ying-Cong Chen, Li Yuan
Technical ReportarXiv 2025
arXivPage
MAR-3D: Progressive Masked Auto-regressor for High-Resolution 3D Generation
Jinnan Chen, Lingting Zhu, Zeyu Hu, Shengju Qian, Yugang Chen, Xin Wang, Gim Hee Lee
IEEE/CVF Conference on Computer Vision and Pattern RecognitionCVPR 2025 Highlight
arXivPageCode
Human Reconstruction
Forge4D
Forge4D: Feed-Forward 4D Human Reconstruction and Interpolation from Uncalibrated Sparse Videos
Yingdong Hu*, Yisheng He*†, Jinnan Chen, Weihao Yuan, Kejie Qiu, Zehong Lin, Siyu Zhu, Zilong Dong, Jun Zhang
Technical ReportarXiv 2025
arXivPage
Reconstructing Close Human Interaction with Appearance and Proxemics Reasoning
Buzhen Huang, Chen Li, Chongyang Xu, Dongyue Lu, Jinnan Chen, Yangang Wang, Gim Hee Lee
IEEE/CVF Conference on Computer Vision and Pattern RecognitionCVPR 2025
arXivPageCode
DiHuR: Diffusion-Guided Generalizable Human Reconstruction
Jinnan Chen, Chen Li, Gim Hee Lee
IEEE/CVF Winter Conference on Applications of Computer VisionWACV 2025
arXiv
Gaussian Splatting
Generalizable Human Gaussians from Single-View Image
Jinnan Chen, Chen Li, Jianfeng Zhang, Lingting Zhu, Buzhen Huang, Hanlin Chen, Gim Hee Lee
International Conference on Learning RepresentationsICLR 2025
arXivPageCode
LIG
Large Images are Gaussians: High-quality Large Image Representation with Levels of 2D Gaussian Splatting
Lingting Zhu, Guying Lin, Jinnan Chen, Xinjie Zhang, Zhenchao Jin, Zhao Wang, Lequan Yu
AAAI Conference on Artificial IntelligenceAAAI 2025
arXivCode
Rigging & Skinning
Auto-Connect
Auto-Connect: Connectivity-Preserving RigFormer with Direct Preference Optimization
Jingfeng Guo*, Jian Liu*, Jinnan Chen†, Shiwei Mao, Changrong Hu, Puhua Jiang, Junlin Yu, Jing Xu, Qi Liu†, Lixin Xu, Zhuo Chen, Chunchao Guo († corresponding author)
Conference on Neural Information Processing SystemsNeurIPS 2025
arXivPage
WS3DPT
Weakly-supervised 3D Pose Transfer with Keypoints
Jinnan Chen, Chen Li, Gim Hee Lee
IEEE/CVF International Conference on Computer VisionICCV 2023
arXivPageCode
Early Work · Imaging & Calibration
Reflection Removal
Single Image Reflection Removal with Absorption Effect
Qian Zheng, Boxin Shi, Jinnan Chen, Xudong Jiang, Ling-Yu Duan, Alex C. Kot
IEEE/CVF Conference on Computer Vision and Pattern RecognitionCVPR 2021
PaperCode
Feature Distillation
Feature Distillation with Guided Adversarial Contrastive Learning
Tao Bai, Jinnan Chen, Jun Zhao, Bihan Wen, Xudong Jiang, Alex Kot
Technical ReportarXiv 2020
arXiv
Plate Glass Calibration
What Does Plate Glass Reveal About Camera Calibration?
Qian Zheng, Jinnan Chen, Zhan Lu, Boxin Shi, Xudong Jiang, Kim-Hui Yap, Ling-Yu Duan, Alex C. Kot
IEEE/CVF Conference on Computer Vision and Pattern RecognitionCVPR 2020
PaperCode

Teaching & Service

Teaching Assistant · NUS

  • 2022CS5340 — Uncertainty Modelling in AI
  • 2022CS5477 — 3D Computer Vision

Reviewer

  • CVPR 2024 – 2026 · ICCV 2025 · ECCV 2026
  • NeurIPS 2024 – 2025 · ICLR 2025 – 2026
  • ICML 2025 – 2026 · AISTATS 2025 – 2026
  • AAAI 2026 · TMLR