Chaoyue Song 宋超越

I am a final-year PhD student at the College of Computing and Data Science, Nanyang Technological University, supervised by Prof. Guosheng Lin and Dr. Fayao Liu. Previously, I earned my Bachelor’s Degree at Shanghai Jiao Tong University. I was fortunate to have an internship at Bytedance Seed, working with Dr. Jiashi Feng and Dr. Jianfeng Zhang.

My research interests lie in computer vision and machine learning, with a current focus on 3D vision (reconstruction, animation, and generation) and generative AI. I am passionate about modeling the dynamic world. If you want to know more about me, please feel free to contact me (chaoyue002 AT e.ntu.edu.sg or chaoyuesong7 AT gmail.com).

Email  /  Google Scholar /  Github /  Twitter /  LinkedIn /  RedNote


I expect to graduate in 2026 and am actively seeking opportunities in both industry and academia.

News

Selected Publications

Puppeteer: Rig and Animate Your 3D Models
Chaoyue Song, Xiu Li, Fan Yang, Zhongcong Xu, Jiacheng Wei, Fayao Liu, Jiashi Feng, Guosheng Lin, and Jianfeng Zhang
arXiv, 2025
Project / Code / arXiv / Video / Data / Slides

MagicArticulate: Make Your 3D Models Articulation-Ready
Chaoyue Song, Jianfeng Zhang, Xiu Li, Fan Yang, Yiwen Chen, Zhongcong Xu, Jun Hao Liew, Xiaoyang Guo, Fayao Liu, Jiashi Feng, and Guosheng Lin
CVPR, 2025
Project / Code / arXiv / Video / Data / Slides

ADHMR: Aligning Diffusion-based Human Mesh Recovery via Direct Preference Optimization
Wenhao Shen, Wanqi Yin, Xiaofeng Yang, Cheng Chen, Chaoyue Song, Zhongang Cai, Lei Yang, Hao Wang, and Guosheng Lin
ICML, 2025
arXiv / Code

High Quality Human Image Animation using Regional Supervision and Motion Blur Condition
Zhongcong Xu*, Chaoyue Song*, Guoxian Song*, Jianfeng Zhang, Jun Hao Liew, Hongyi Xu, You Xie, Linjie Luo, Guosheng Lin, Jiashi Feng, and Mike Zheng Shou
arXiv, 2024
arXiv

REACTO: Reconstructing Articulated Objects from a Single Video
Chaoyue Song, Jiacheng Wei, Chuan-Sheng Foo, Guosheng Lin, and Fayao Liu
CVPR, 2024
Project / Code / arXiv / Video / Data

Sync4D: Video Guided Controllable Dynamics for Physics-Based 4D Generation
Zhoujie Fu*, Jiacheng Wei*, Wenhao Shen, Chaoyue Song, Xiaofeng Yang, Fayao Liu, Xuelei Yang, and Guosheng Lin
arXiv, 2024
Project / arXiv

MoDA: Modeling Deformable 3D Objects from Casual Videos
Chaoyue Song, Jiacheng Wei, Tianyi Chen, Yiwen Chen, Chuan-Sheng Foo, Fayao Liu, and Guosheng Lin
IJCV, 2024
Project / Code / arXiv / Video

Unsupervised 3D Pose Transfer with Cross Consistency and Dual Reconstruction
Chaoyue Song, Jiacheng Wei, Ruibo Li, Fayao Liu, and Guosheng Lin
TPAMI, 2023
Project / Code / arXiv

3D Pose Transfer with Correspondence Learning and Mesh Refinement
Chaoyue Song, Jiacheng Wei, Ruibo Li, Fayao Liu, and Guosheng Lin
NeurIPS, 2021
Project / Code / arXiv / Video / Video (in Chinese)


Project

Dense QR Decoder Based on TensorFlow Lite
National Undergraduate IOT Design Contest in China: First Prize in Finals (Top 35 of the 2000 teams), 2019
Video
We developed an APP which can decodes plenty of QR codes at the same time.


Awards

  • Singapore International Graduate Award (SINGA), 2022
  • Outstanding Graduate of Shanghai, 2020
  • National Undergraduate IOT Design Contest in China: First Prize in Final Contest (Top 35 of the 2000 teams), 2019
  • Outstanding Scholarship of Shanghai Jiao Tong University, 2017, 2018, 2019
  • Excellent Student Cadre of Shanghai Jiao Tong University, 2018
Talks

  • [09/2025 @ TechBeat (将门)] Automatic Rigging and Animation, Slides / Link
  • [03/2025 @ AnySyn3D] Automatic Rigging and Skinning, Slides / Link

Services

  • Conference reviewer: NeurIPS 2024/2025, ICLR 2025/2026, CVPR 2025, ICML 2025, ICCV 2025, ACM MM 2025, SIGGRAPH Asia 2025, WACV 2026
  • Journal reviewer: TMM, TCSVT
Visitors


Template borrowed from this awesome website.