Chuanxia Zheng

@ChuanxiaZ

Assistant Professor @NTUsg | Postdoc @Oxford_VGG | PhD @NTUsg

Oxford, United Kingdom

chuanxiaz.com

Joined January 2020

Chuanxia Zheng
@ChuanxiaZ
Jul 10
👋AnyHand introduces a large synthetic RGB-D dataset for 3D hand pose estimation, showing that carefully designed synthetic supervision can substantially improve downstream performance. An exciting resource for research in 3D hand understanding. All sources are available now
Chen Si
@Chen_Si_CS
Jul 6
Meet AnyHand 🖐️ — the largest synthetic RGB-D dataset for 3D hand pose estimation to date. With diverse, realistic hand data at unprecedented scale, AnyHand sets a new state of the art in 3D hand pose estimation. Excited about its potential for robot learning and manipulation
00:00
Chuanxia Zheng
@ChuanxiaZ
Jul 5
How can we build 4D world models from any view, at any time, with physical consistency—without correct data? To push this direction, we introduce Syn4D—a large-scale synthetic multi-view dynamic scene dataset with dense, complete, and physically accurate geometric annotations.
Zeren Jiang
@CodyJzr
Jul 4
🎁 We are pleased to introduce Syn4D, a large-scale multiview synthetic dataset for dynamic scenes, accepted at #ECCV2026. The complete dataset, including its dense geometric annotations, is now publicly available. 🌐 Project: jzr99.github.io/Syn4D/ 💻 GitHub:
00:00
Chuanxia Zheng
@ChuanxiaZ
Jun 16
📢Excited to share Particulate V2! 📌40× more training data than V1 📌a redesigned architecture with kinematic prompts' articulation 📌 significantly improved generalization to novel categories 📌 supports generating simulator-ready articulated assets from real-world images
RuiningLi
@RayLi234
Jun 15
🚀 Introducing Instruct-Particulate, our new model for inferring articulated structures from static 3D meshes, with significantly improved generalization to novel object categories and support for kinematic prompting. To achieve this, we scaled our training data 40× and
00:00
Chuanxia Zheng
@ChuanxiaZ
Jun 5
If you’re attending CVPR, stop by Poster #586 this Saturday to check out Particulate! Unfortunately, I won’t be able to attend in person due to visa issues, but @RetnRosa will be presenting the work. Other authors from @Oxford_VGG may also be around to chat about the project.
RuiningLi
@RayLi234
Dec 16, 2025
Introducing Particulate: a feed-forward model for 3D object articulation 💻✂️👓🧳 Particulate gives you a fully articulated 3D object, including part segmentation, kinematic structure & motion constraints, in a single forward pass in ~10secs. 🏅SOTA performance! 💡GenAI
00:00
Chuanxia Zheng
@ChuanxiaZ
May 15
This is an amazing project led by @Mattzh1314. I thought LLMs could already code 3D, but I did not expect such realistic, complex, and fine-grained articulation generation. It completely changed my view of 3D agents — this could be a major step toward real industrial agents.
RuiningLi
@RayLi234
May 15
🚀 Introducing Articraft, a coding agent for articulated 3D asset creation. Articraft writes code, executes it, receives validation feedback, and refines the result into simulation-ready 3D assets with parts, joints, and motion. We’re also releasing Articraft-10K: 10,000+
00:00