Han Yan

Han Yan (严涵)

I am a third-year Ph.D. student at Shanghai Jiao Tong University (SJTU), advised by Prof. Chao Ma. I received my bachelor's degree from Artificial Intelligence Honor Class at SJTU in 2023, supervised by Prof. Chao Ma.

I was a research intern at Tencent XR Vision Lab, working with Yang Li and Pan Ji. I was a research intern at Bytedance, working with Celong Liu and Xing Mei.

I am interested in video generation and 3D computer vision and graphics.

Email / Scholar / Github

News

News (Jul 2024): One paper is accepted to SIGGRAPH Asia 2024 (Conferences Track).
News (Jul 2024): One paper is accepted to ECCV 2024.
News (Mar 2024): One paper is accepted to ACM Transactions on Graphics (SIGGRAPH) 2024.
News (Feb 2023): One paper is accepted to CVPR 2023.

Publications

	PhyCAGE: Physically Plausible Compositional 3D Asset Generation from a Single Image Han Yan, Mingrui Zhang, Yang Li, Chao Ma, Pan Ji arXiv, 2024 project page / arXiv / video PhyCAGE generates physically plausible compositional 3D assets from a single image.
	Frankenstein: Generating Semantic-Compositional 3D Scenes in One Tri-Plane Han Yan, Yang Li, Zhennan Wu, Shenzhou Chen, Weixuan Sun, Taizhang Shang, Weizhe Liu, Tian Chen, Xiaqiang Dai, Chao Ma, Hongdong Li, Pan Ji SIGGRAPH Asia, 2024 project page / arXiv / video / code Frankenstein generates semantic-compositional 3D scenes in a single forward pass.
	NeuSDFusion: A Spatial-Aware Generative Model for 3D Shape Completion, Reconstruction, and Generation Ruikai Cui, Weizhe Liu, Weixuan Sun, Senbo Wang, Taizhang Shang, Yang Li, Xibin Song, Han Yan, Zhennan Wu, Shenzhou Chen, Hongdong Li, Pan Ji ECCV, 2024 project page / arXiv NeuSDFusion is a novel spatial-aware 3D shape generation framework.
	Blockfusion: Expandable 3D Scene Generation using Latent Tri-plane Extrapolation Zhennan Wu, Yang Li, Han Yan, Taizhang Shang, Weixuan Sun, Senbo Wang, Ruikai Cui, Weizhe Liu, Hiroyuki Sato, Hongdong Li, and Pan Ji ACM Transaction on Graphics (SIGGRAPH), 2024 project page / arXiv / video / code Blockfusion directly generate large unbounded 3D scene.
	PlenVDB: Memory Efficient VDB-Based Radiance Fields for Fast Training and Rendering Han Yan, Celong Liu, Chao Ma, Xing Mei CVPR, 2023 project page / pdf / video / code PlenVDB directly learns the VDB data to achieve NeRF acceleration.

Selected Awards

Best Bachelor Thesis, Shanghai Jiao Tong University (Top 1%), 2023.
Outstanding Graduates, Shanghai Jiao Tong University, 2023.

Services

Reviewer: CVPR, ICCV, NeurIPS, ICLR, AAAI, WACV, TGRS

Miscellanea

Sports: ⚽️🇦🇷🔟
Music: R&B/Hiphop/Alternative, e.g. NIKI.
Manga: One Piece

Thanks to Jon Barron for the template, and to Yiheng Pi for taking my profile photo.