Jing Lin 林靖

My research focuses on 3D generative models and multimodal intelligence for understanding and interacting with the physical world.

PhD student at MMLab, Nanyang Technological University,
advised by Prof. Ziwei Liu.

News

JUL 2026

ArtiAtlas accepted to SIGGRAPH Asia 2026.

APR 2026

Seed3D 2.0 released: sharper geometry, richer materials, interactive scenes.

FEB 2026

TopoMesh and ViLearn accepted to CVPR 2026.

JAN 2026

ViMoGen and EchoMotion accepted to ICLR 2026.

Technical Reports

Technical Report · 2026

Seed3D 2.0: Advancing High-Fidelity Simulation-Ready 3D Content Generation

Seed3D Team, ByteDance Seed · Jing Lin Core Contributor

Full author list

Diandian Gu, Jing Lin, Gaohong Liu, Jiahang Liu, Su Ma, Guang Shi, Jun Wang, Qinlong Wang, Qianyi Wu, Zhongcong Xu, Xuanyu Yi, Zihao Yu, Jianfeng Zhang, Zhuolin Zheng, Yifan Zhu, Rui Chen, Hengkai Guo, Xiaoyang Guo, Mingcong Han, Xu Han, Xiu Li, Yixun Liang, Weiqiang Lou, Junzhe Lu, Guan Luo, Minghan Qin, Shuguang Wang, Yuang Wang

High-fidelity geometry, PBR materials, and interactive 3D scenes.

Project Paper

Technical Report · 2025

Seed3D 1.0: From Images to High-Fidelity Simulation-Ready 3D Assets

Seed3D Team, ByteDance Seed · Jing Lin Core Contributor

Full author list

Jiashi Feng, Xiu Li, Jing Lin, Jiahang Liu, Gaohong Liu, Weiqiang Lou, Su Ma, Guang Shi, Qinlong Wang, Jun Wang, Zhongcong Xu, Xuanyu Yi, Zihao Yu, Jianfeng Zhang, Yifan Zhu, Rui Chen, Jinxin Chi, Zixian Du, Li Han, Lixin Huang, Kaihua Jiang, Yuhan Li, Guan Luo, Shuguang Wang, Qianyi Wu, Fan Yang, Junyang Zhang, Xuanmeng Zhang

Turning a single image into textured 3D assets ready for simulation.

Project Paper

Publications

16 papers

* Equal contribution · † Project lead Newest first · Click an image to enlarge

2026

SIGGRAPH Asia 2026To appear

ArtiAtlas: A Holistic Ecosystem for Diverse 3D Articulation Modeling

Junzhe Lu, Jing Lin^†, Ziang Cao, Haoqian Wang, Ziwei Liu, Jianfeng Zhang

From static 3D assets to articulated, functional objects.

CVPR 2026

TopoMesh: High-Fidelity Mesh Autoencoding via Topological Unification

Guan Luo, Xiu Li, Rui Chen, Xuanyu Yi, Jing Lin, Chia-Hao Chen, Jiahang Liu, Song-Hai Zhang, Jianfeng Zhang

A shared topology for accurate, high-resolution mesh autoencoding.

Project Paper

CVPR 2026

ViLearn: Accelerating Training Convergence of Image-to-3D Generation via Visibility Learning

Rui Chen, Jianfeng Zhang, Jing Lin, Xuanyu Yi, Yixun Liang, Guan Luo, Xiu Li, Zeming Li, Ping Tan

Learning visibility structure to accelerate image-to-3D training.

Paper

ICLR 2026

The Quest for Generalizable Motion Generation: Data, Model, and Evaluation

Jing Lin^*, Ruisi Wang^*, Junzhe Lu^*, Ziqi Huang, Guorui Song, Ailing Zeng, Xian Liu, Chen Wei, Wanqi Yin, Qingping Sun, Zhongang Cai, Lei Yang, Ziwei Liu

Bringing video priors to generalizable human motion generation.

Project Paper Code

ICLR 2026

EchoMotion: Unified Human Video and Motion Generation via Dual-Modality Diffusion Transformer

Yuxiao Yang, Hualian Sheng, Sijia Cai, Jing Lin, Jiahao Wang, Bing Deng, Junzhe Lu, Haoqian Wang, Jieping Ye

A dual-modality diffusion transformer for joint video and motion generation.

Project Paper Code

2025

ICCV 2025 ORAL

DPoser-X: Diffusion Model as Robust 3D Whole-body Human Pose Prior

Junzhe Lu^*, Jing Lin^*, Hongkun Dou, Ailing Zeng, Yue Deng, Xian Liu, Zhongang Cai, Lei Yang, Yulun Zhang, Haoqian Wang, Ziwei Liu

A diffusion prior for expressive whole-body pose modeling.

Project Paper Code

CVPR 2025

ChatHuman: Chatting about 3D Human with Tools

Jing Lin^*, Yao Feng^*, Weiyang Liu, Michael J. Black

Reasoning about 3D humans through conversation and specialized tools.

Project Paper

2024

CVPR 2024

ChatPose: Chatting about 3D Human Pose

Yao Feng, Jing Lin, Sai Kumar Dwivedi, Yu Sun, Priyanka Patel, Michael J. Black

Connecting natural language and 3D human pose.

Project Paper

2023

NeurIPS 2023

Motion-X: A Large-scale 3D Expressive Whole-body Human Motion Dataset

Jing Lin^*, Ailing Zeng^*, Shunlin Lu^*, Yuanhao Cai, Ruimao Zhang, Haoqian Wang, Lei Zhang

A large-scale dataset for expressive whole-body human motion.

Project Paper

CVPR 2023

One-Stage 3D Whole-Body Mesh Recovery with Component Aware Transformer

Jing Lin, Ailing Zeng, Haoqian Wang, Lei Zhang, Yu Li

Recovering the body, hands, and face together in a single stage.

Project Paper Video

2022

ICML 2022

Flow-Guided Sparse Transformer for Video Deblurring

Jing Lin^*, Yuanhao Cai^*, Xiaowan Hu, Haoqian Wang, Youliang Yan, Xueyi Zou, Henghui Ding, Yulun Zhang, Radu Timofte, Luc Van Gool

Flow-guided sparse attention for sharp, temporally coherent video.

Code Paper

ICML 2022

Unsupervised Flow-Aligned Sequence-to-Sequence Learning for Video Restoration

Jing Lin^*, Xiaowan Hu^*, Yuanhao Cai, Haoqian Wang, Youliang Yan, Xueyi Zou, Yulun Zhang, Luc Van Gool

Learning video restoration from unpaired low-quality sequences.

Code Paper

CVPR 2022

Mask-Guided Spectral-Wise Transformer for Efficient Hyperspectral Image Reconstruction

Yuanhao Cai^*, Jing Lin^*, Xiaowan Hu, Haoqian Wang, Xin Yuan, Henghui Ding, Yulun Zhang, Radu Timofte, Luc Van Gool

Spectral attention for efficient hyperspectral reconstruction.

Code Paper

ECCV 2022

Coarse-to-Fine Sparse Transformer for Hyperspectral Image Reconstruction

Yuanhao Cai^*, Jing Lin^*, Xiaowan Hu, Haoqian Wang, Xin Yuan, Yulun Zhang, Radu Timofte, Luc Van Gool

Coarse-to-fine sparse attention for spectral image reconstruction.

Code Paper

NeurIPS 2022

Degradation-Aware Unfolding Half-Shuffle Transformer for Spectral Compressive Imaging

Yuanhao Cai^*, Jing Lin^*, Haoqian Wang, Xin Yuan, Yulun Zhang, Radu Timofte, Luc Van Gool

Combining degradation modeling, unfolding, and transformers.

Code Paper

CVPRW 2022 ORAL

MST++: Multi-stage Spectral-wise Transformer for Efficient Spectral Reconstruction

Yuanhao Cai^*, Jing Lin^*, Zudi Lin, Haoqian Wang, Yulun Zhang, Hanspeter Pfister, Radu Timofte, Luc Van Gool

Multi-stage spectral attention for efficient spectral reconstruction.

Code Paper

About

Background

I am pursuing a PhD at Nanyang Technological University, supervised by Prof. Ziwei Liu. I received my master’s degree from Tsinghua University, advised by Haoqian Wang, and my B.Eng. in Automation from Harbin Institute of Technology (Shenzhen).

My earlier work focused on video restoration and computational imaging. Today, I explore generative 3D models and human-centric perception, generation, and understanding.

Explore my open-source work ↗

Selected honors

2024
Excellent Graduate & Excellent Master Thesis AwardTsinghua University
2023
National ScholarshipTsinghua University
2022
Winner, NTIRE Spectral Reconstruction ChallengeCVPR
2021
Third Place, NTIRE Video Super-Resolution ChallengeCVPR

Earlier honors

Excellent Graduate, HIT (Shenzhen), 2021.
National Scholarship, HIT (Shenzhen), 2019.
First Class Scholarship, 2019, 2020, 2022.

Academic service

Reviewer for TPAMI, IJCV, CVPR, ECCV, ICCV, and NeurIPS.