Bio

I am a Ph.D. student at ShanghaiTech University, jointly supervised by Prof. Shenghua Gao (The University of Hong Kong) and Prof. Lan Xu (ShanghaiTech University).

My research interests lie at the intersection of computer graphics and vision, with a focus on 3D representation learning and generative models. Recently, I have been exploring 3D scene-level generative models that can benefit spatial intelligence and embodied AI. I am passionate about new ideas and collaborations.

Experience

VAST, Research Intern  ·  Jan. 2026 – Present
Admitted through the VStar Program.

Tencent Hunyuan 3D, Research Intern  ·  May 2025 – Jan. 2026
Admitted through the Qingyun Program (青云计划).

Publications

* denotes equal contribution

《X-Part: high fidelity and structure coherent shape decomposition》
CVPR 2026
Xinhao Yan*, Jiachen Xu*, Yang Li, Changfeng Ma, Yunhan Yang, Chunshi Wang, Zibo Zhao, Zeqiang Lai, Yunfei Zhao, Zhuo Chen, Chunchao Guo
《P3-SAM: Native 3D Part Segmentation》
Arxiv
Changfeng Ma, Yang Li, Xinhao Yan, Jiachen Xu, Yunhan Yang, Chunshi Wang, Zibo Zhao, Zeqiang Lai, Yunfei Zhao, Zhuo Chen, Chunchao Guo
《Hunyuan3D Studio: End-to-End AI Pipeline for Game-Ready 3D Asset Generation》
Technical Report
《CAST: Component-Aligned 3D Scene Reconstruction from an RGB Image》
SIGGRAPH 2025 — Best Paper Award
Kaixin Yao*, Longwen Zhang*, Xinhao Yan, Yan Zeng, Qixuan Zhang, Wei Yang, Lan Xu, Jiayuan Gu, Jingyi Yu
《PREF: Phasorial Embedding Fields for Compact Neural Representation》
Arxiv
Binbin Huang*, Xinhao Yan*, Anpei Chen, Shenghua Gao, Jingyi Yu
《Dual-Space NeRF: Learning Animatable Avatars and Scene Lighting in Separate Spaces》
3DV 2022
Yihao Zhi*, Shenhan Qian*, Xinhao Yan*, Shenghua Gao