# Donny Y. Chen

> Donny Chen - Research Scientist at ByteDance Seed (Singapore)

## About

Donny Y. Chen is a Singapore-based Research Scientist, working on 3D/4D vision. ALL VIEWS ARE SOLELY HIS OWN.

## Publications


### World-R1: Reinforcing 3D Constraints for Text-to-Video Generation

- Venue: ICML 2026
- Authors: Weijie Wang*, Xiaoxuan He*, Youping Gu*, Yifan Yang, Zeyu Zhang, Yefei He, Yanbo Ding, Xirui Hu, Donny Y. Chen, Zhiyuan He, Yuqing Yang, Bohan Zhuang
- Links:
  - arXiv: https://arxiv.org/abs/2604.24764
  - code: https://github.com/microsoft/World-R1
  - project page: https://aka.ms/world-r1
  - Paper of the Day #1: https://huggingface.co/papers/2604.24764

### Feed-Forward 3D Scene Modeling: A Problem-Driven Perspective

- Venue: Survey 2026
- Authors: Weijie Wang*, Qihang Cao*, Sensen Gao*, Donny Y. Chen†, Haofei Xu, Wenjing Bian, Songyou Peng, Tat-Jen Cham, Chuanxia Zheng, Andreas Geiger, Jianfei Cai, Jia-Wang Bian, Bohan Zhuang
- Links:
  - arXiv: https://arxiv.org/abs/2604.14025
  - code: https://github.com/ziplab/Awesome-Feed-Forward-3D
  - project page: https://ff3d-survey.github.io/

### Depth Anything 3: Recovering the Visual Space from Any Views

- Venue: Tech Report 2025
- Authors: Haotong Lin*, Sili Chen*, Jun Hao Liew*, Donny Y. Chen*, Zhenyu Li, Guang Shi, Jiashi Feng, Bingyi Kang*
- Links:
  - arXiv: https://arxiv.org/abs/2511.10647
  - code: https://github.com/ByteDance-Seed/depth-anything-3
  - project page: https://depth-anything-3.github.io/
  - demo: https://huggingface.co/spaces/depth-anything/depth-anything-3
  - gallery: https://depth-anything-3.github.io/gallery.html
  - news: https://seed.bytedance.com/en/blog/seed-research-depth-anything-3-a-single-transformer-architecture-for-space-reconstruction-from-any-views?view_from=content_recommend
  - Spaces of the Week #4: https://huggingface.co/spaces?date=2025-W47
  - Paper of the Day #2: https://huggingface.co/papers/2511.10647

### Trace Anything: Representing Any Video in 4D via Trajectory Fields

- Venue: ICLR 2026
- Authors: Xinhang Liu, Yuxi Xiao, Donny Y. Chen, Jiashi Feng, Yu-Wing Tai, Chi-Keung Tang, Bingyi Kang
- Links:
  - arXiv: https://arxiv.org/abs/2510.13802
  - code: https://github.com/ByteDance-Seed/TraceAnything
  - project page: https://trace-anything.github.io/

### Revisiting Depth Representations for Feed-Forward 3D Gaussian Splatting

- Venue: 3DV 2026
- Authors: Duochao Shi*, Weijie Wang*, Donny Y. Chen, Zeyu Zhang, Jia-Wang Bian, Bohan Zhuang
- Links:
  - arXiv: https://arxiv.org/abs/2506.05327
  - code: https://github.com/aim-uofa/PM-Loss
  - project page: https://aim-uofa.github.io/PMLoss/

### ZPressor: Bottleneck-Aware Compression for Scalable Feed-Forward 3DGS

- Venue: NeurIPS 2025
- Authors: Weijie Wang, Donny Y. Chen, Zeyu Zhang, Duochao Shi, Akide Liu, Bohan Zhuang
- Links:
  - arXiv: https://arxiv.org/abs/2505.23734
  - code: https://github.com/ziplab/ZPressor
  - project page: https://lhmd.top/zpressor/

### Explicit Correspondence Matching for Generalizable Neural Radiance Fields

- Venue: TPAMI 2025
- Authors: Yuedong Chen, Haofei Xu, Qianyi Wu, Chuanxia Zheng, Tat-Jen Cham, Jianfei Cai
- Links:
  - arXiv: http://arxiv.org/abs/2304.12294
  - code: https://github.com/donydchen/matchnerf
  - project page: https://donydchen.github.io/matchnerf/

### MVSplat360: Feed-Forward 360 Scene Synthesis from Sparse Views

- Venue: NeurIPS 2024
- Authors: Yuedong Chen, Chuanxia Zheng, Haofei Xu, Bohan Zhuang, Andrea Vedaldi, Tat-Jen Cham, Jianfei Cai
- Links:
  - arXiv: https://arxiv.org/abs/2411.04924
  - code: https://github.com/donydchen/mvsplat360
  - project page: https://donydchen.github.io/mvsplat360

### MVSplat: Efficient 3D Gaussian Splatting from Sparse Multi-View Images

- Venue: ECCV 2024 (Oral)
- Authors: Yuedong Chen, Haofei Xu, Chuanxia Zheng, Bohan Zhuang, Marc Pollefeys, Andreas Geiger, Tat-Jen Cham, Jianfei Cai
- Links:
  - arXiv: https://arxiv.org/abs/2403.14627
  - code: https://github.com/donydchen/mvsplat
  - project page: https://donydchen.github.io/mvsplat
  - Hacker News: https://news.ycombinator.com/item?id=41222655
  - Trendshift #20: https://trendshift.io/repositories/8862
  - Most Influential ECCV Paper #13: https://resources.paperdigest.org/2025/09/most-influential-eccv-papers-2025-09-version/

### MuRF: Multi-Baseline Radiance Fields

- Venue: CVPR 2024
- Authors: Haofei Xu, Anpei Chen, Yuedong Chen, Christos Sakaridis, Yulun Zhang, Marc Pollefeys, Andreas Geiger, <i>et al.</i>
- Links:
  - arXiv: https://arxiv.org/abs/2312.04565
  - code: https://github.com/autonomousvision/murf
  - project page: https://haofeixu.github.io/murf/

### Sem2NeRF: Converting Single-View Semantic Masks to Neural Radiance Fields

- Venue: ECCV 2022
- Authors: Yuedong Chen, Qianyi Wu, Chuanxia Zheng, Tat-Jen Cham, Jianfei Cai
- Links:
  - arXiv: https://arxiv.org/abs/2203.10821
  - code: https://github.com/donydchen/sem2nerf
  - project page: https://donydchen.github.io/sem2nerf/
  - demo video: https://www.youtube.com/watch?v=cYr3Dz8N_9E

## Projects & Talks

### Talks
- Feed-forward NVS from Sparse Inputs — hosted by Lior Fritz
- Feed-forward Novel View Synthesis — hosted by Joe Polin

### Projects / demos
- Oral presentation at ICLR 2026 
- Invited talk at 3DV25 Nectar Track
- Invited talk at AJCAI 2024
- Oral presentation at ECCV 2024 
- Invited talk at SHUZIHUANYU
- Invited talk at 3DCVer 
- Demo at Monash Uni. Open Day 2022
- A popular replication of GANimation


## Contact

- Email: donny.chen@outlook.sg

- Email: mailto:donny.chen@outlook.sg
- Google Scholar: https://scholar.google.com/citations?user=GqgGZlQAAAAJ
- ORCID: https://orcid.org/0000-0003-0943-1512
- GitHub: https://github.com/donydchen
- LinkedIn: https://www.linkedin.com/in/donydchen
- BlueSky: https://bsky.app/profile/donydchen.bsky.social
- Twitter: https://x.com/donydchen

## Surfaces

- Homepage: https://donydchen.github.io/
- Documentation / template guide: https://donydchen.github.io/docs/
- License: https://donydchen.github.io/LICENSE/
- Atom feed: https://donydchen.github.io/feed.xml
- Sitemap: https://donydchen.github.io/sitemap.xml

## Machine-readable resources

- Agent skills index: https://donydchen.github.io/.well-known/agent-skills/index.json
- MCP server card: https://donydchen.github.io/.well-known/mcp/server-card.json
- A2A agent card: https://donydchen.github.io/.well-known/agent-card.json
- API catalog: https://donydchen.github.io/.well-known/api-catalog
- OAuth authorization server metadata: https://donydchen.github.io/.well-known/oauth-authorization-server
- OAuth protected resource metadata: https://donydchen.github.io/.well-known/oauth-protected-resource