Yaoan Gao 高耀安

M.Sc. Candidate

Zhejiang University

Biography

Hi, this is Yaoan Gao. I am a 3rd-year (2022~) M.Sc. student in the State Key Laboratory of CAD&CG, Zhejiang University, advised by Prof.Weiwei Xu. My primary research interests lie in inverse rendering and real-time rendering. I am looking for internship 2025 summer.

Interests

Inverse Rendering
Real-time Rendering

Education

M.Sc. in Computer Science, 2022
Zhejiang University
B.Eng. in Automation, 2018
Xi'an Jiaotong University

Featured Publications

Differentiable Linearly Transformed Cosines for Inverse Area Light Shading

Preprint

A novel inverse rendering method that reconstruct geometry and material of an object, achieving superior fidelity within 15 minutes.

Yaoan Gao 高耀安, Jiamin Xu, James Tompkin, Qi Wang, Zheng Dong, Hujun Bao, Yujun Shen, Huamin Wang, Weiwei Xu

Gaussian Surfel Splatting for Live Human Performance Capture

In ACM Trans. on Graphics, 43(6), (Proc. ACM SIGGRAPH Asia 2024)

A novel regressed-surface-point-based method, to leverage Gaussian surfel splatting and blending-based appearance enhancement, for human live free-view rendering from 4 RGBD sensors.

Zheng Dong, Ke Xu, Yaoan Gao 高耀安, Hujun Bao, Weiwei Xu, Rynson W.H Lau

Gaussian Surfel Splatting for Live Human Performance Capture

SAILOR: Synergizing Radiance and Occupancy Fields for Live Human Performance Capture

In ACM Trans. on Graphics, 42(6), (Proc. ACM SIGGRAPH Asia 2023)

A generalizable method for human free-view rendering and reconstruction from very sparse (e.g., 4) RGBD streams, achieving near real-time performance under acceleration.

Zheng Dong, Ke Xu, Yaoan Gao 高耀安, Qilin Sun, Hujun Bao, Weiwei Xu, Rynson W.H Lau

Industry Experience

Research Intern

Ant Group

April 2023 – Present Hangzhou

Exploring digital human and inverse rendering, mainly reconstruction of PBR material.
Participated in and completed the digital human project.
Leading the inverse rendering project.
Two technical summary papers:
- One accepted by SIGGRAPH Asia 2023 (Journal Track).
- One submitted to SIGGRAPH 2025 (Conference Track).
Two national invention patent.