Hi! I’m Hanyuan Xiao. I will soon join
Zoom as a Video AI Engineer
based in San Jose, California.
I earned my Ph.D. in Computer Science from the
University of Southern California,
where I was advised by Dr.
Yajie Zhao
in the Vision & Graphics Lab
at the
Institute for Creative Technologies (ICT).
My research connects 3D computer vision, computer graphics, and generative AI.
I focus on reconstructing, rendering, and editing 3D scenes, with experience
in neural rendering, 3D Gaussian Splatting, and human performance capture.
More recently, I have been exploring diffusion models for video generation
and vision-language models for scene understanding.
Alongside my academic research, I have worked on simulation and synthetic
data at Axon. I enjoy bringing research ideas into practical systems that
help us understand and create visual worlds.
Publication & Patent
Light Sampling Field and BRDF Representation for Physically-based Neural Rendering
ICLR 2023Jing Yang*, Hanyuan Xiao*, Wenbin Teng, Yunxuan Cai, Yajie Zhao
Project Page | Paper | GitHub
A novel lighting representation that enables high-performance and lightweight physically-based neural shader
