Brian Chao

I'm a 2nd year PhD student at Stanford University working in the Stanford Computational Imaging Lab, advised by Prof. Gordon Wetzstein. I'm grateful to be supported by the NSF GRFP and the Stanford Graduate Fellowship.

My research is in mainly in computational imaging, displays, and optics, where I focus on the co-design of hardware and algorithms to enable new imaging and display capabilities. I'm also broadly interested in computer graphics, vision, and machine learning.

Prior to coming to Stanford, I recieved a B.S. in Electrical Engineering from National Taiwan University in 2021, where I worked with Prof. Homer H. Chen and Prof. Yu-Chiang Frank Wang.

Email  /  CV  /  Google Scholar  /  Twitter  /  Github

profile photo


High Brighness Holographic Projection
Brian Chao, Manu Gopakumar, Suyeon Choi, Gordon Wetzstein
Optics Letters, 2023

A novel light-efficiency loss function, AI-driven CGH techniques, and camera-in-the-loop calibration greatly improves holographic projector brightness and image quality.

Neural Holographic Displays for Virtual Reality
Brian Chao*, Suyeon Choi*, Manu Gopakumar*, Gun-Yeal Lee, Jonghyun Kim, Gordon Wetzstein
ACM SIGGRAPH Emerging Technologies, 2023

Live demonstration of state-of-the-art image quality, full-color, 3D, holographic VR near-eye displays that supports natural accommodation.

Time-Division Multiplexing Light Field Display With Learned Coded Aperture
Brian Chao*, Chang-Le Liu*, Homer H. Chen
IEEE Transactions on Image Processing, 2022

Using coded apertures and a learning-based light field display optimization pipeline to reproduce correct defocus blurs for better accommodation cues.

Robust Light Field Synthesis From Stereo Images With Left-Right Geometric Consistency
Brian Chao, Chang-Le Liu, Homer H. Chen
IEEE International Conference on Image Processing (ICIP), 2021

Leveraging geoemtric consistency in stereo images to synthesize high-quality light fields.

Self-Supervised Deep Learning for Fisheye Image Rectification
Brian Chao*, Pin-Lun Hsu*, Hung-yi Lee, Y.C. Frank Wang
IEEE Internation Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2020

We propose an image-to-image translation algorithm based on generative adversarial networks that rectifies fisheye images without the need of paired training data.

scTIE: data integration and inference of gene regulation using single-cell temporal multimodal data
Yingxin Lin, Tung-Yu Wu, Xi Chen, Sheng Wan, Brian Chao, Jingxue Xin, Jean Y.H. Yang, Wing H. Wong Y.X. Rachel Wang,
Genome Research, 2023

Using optimal transport to infer regulatory relationships predictive of cellular state changes in single-cell temporal and multimodal data.

Website source code from here.