Guangzhao (Alex) He

I'm a senior undergraduate majoring in Computer Science at Chu Kochen Honors College, Zhejiang University. I currently hold a GPA of 3.99/4.0 and expect to receive my degree in June, 2025.

I've been doing research at the intersection of Computer Vision and Graphics, working closely with Prof. Xiaowei Zhou and Prof. Sida Peng. I'm now a research intern with Prof. Jiajun Wu at Stanford University.

I also produce music and DJ under the alias ELYKZ, experimenting among the genres of House, Hip-hop and New-age.

Email  /  CV  /  Google Scholar  /  X  /  Github  /  Spotify

News

• [2024.06] I'll be joining Stanford Vision and Learning Lab supervised by Prof. Jiajun Wu and Prof. Shangzhe Wu
• [2024.01] Our work 4K4D is accepted to CVPR 2024
• [2023.07] Our work EasyVolcap is accepted to SIGGRAPH Asia 2023 TC

Publications

My research interests lie at the intersection of Vision and Graphics, particularly in the representation and understanding of dynamic 3D scenes, with the goal of enabling machines to perceive the dynamic and diverse world as humans do.

A feed-forward pipeline that registers any object template onto a sequence of non-rigidly deforming point clouds, with 4.6x faster inference speed and 2x better accuracy than previous SOTA.

A feed-forward pipeline that registers any object template onto a sequence of non-rigidly deforming point clouds, with 4.6x faster inference speed and 2x better accuracy than previous SOTA.

A novel point-based 4D representation reconstructed with multi-view videos, which can be rendered at 4k 200+ FPS with state-of-the-art quality on a single RTX 4090.

A Python & PyTorch library for accelerating volumetric video research, particularly in the area of neural dynamic scene representation, reconstruction, and rendering.

Template stolen from Jon Barron.