Brian Chao

Brian Chao

Auto-generated profile, based on publicly available information

Brian Chao

Stanford University, United States of America

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
27 July 2025 in ACM Transactions on Graphics
Verified
Journal Article
Open access
SCSuyeon Choi
Suyeon Choi
BCBrian Chao
Brian Chao
JYJacqueline Yang
Jacqueline Yang
MGManu Gopakumar
Manu Gopakumar
GWGordon Wetzstein
Gordon Wetzstein
State-of-the-art neural rendering methods optimize Gaussian scene representations from a few photographs for novel-view synthesis. Building on these representations, we develop an efficient algorithm, dubbed Gaussian Wave Splatting, to turn these Gaussians into holograms. Unlike existing computergenerated holography (CGH) algorithms, Gaussian Wave Splatting supports accurate occlusions and view-dependent effects for photorealistic scenes by leveraging recent advances in neural rendering. Specifically, we derive a closed-form solution for a 2D Gaussian-to-hologram transform that supports occlusions and alpha blending. Inspired by classic computer graphics techniques, we also derive an efficient approximation of the aforementioned process in the Fourier domain that is easily parallelizable and implement it using custom CUDA kernels. By integrating emerging neural rendering pipelines with holographic display technology, our Gaussian-based CGH framework paves the way for next-generation holographic displays.

3 December 2024
Verified
Conference Paper
Open access
BCBrian Chao
Brian Chao
MGManu Gopakumar
Manu Gopakumar
SCSuyeon Choi
Suyeon Choi
JKJonghyun Kim
Jonghyun Kim
LSLiang Shi
Liang Shi
GWGordon Wetzstein
Gordon Wetzstein

26 July 2023
Verified
Conference Paper
Open access
SCSuyeon Choi
Suyeon Choi
MGManu Gopakumar
Manu Gopakumar
BCBrian Chao
Brian Chao
GLGun-Yeal Lee
Gun-Yeal Lee
JKJonghyun Kim
Jonghyun Kim
GWGordon Wetzstein
Gordon Wetzstein
By manipulating light as a wavefront, holographic displays have the potential to revolutionize virtual reality (VR) and augmented reality (AR) systems. These displays support 3D focus cues for visual comfort, vision correcting capabilities, and high light efficiency. However, despite their incredible promise, holographic displays have consistently been hampered by poor image quality. Recently, artificial intelligence–driven computer-generated holography (CGH) algorithms have emerged as a solution to this obstacle. On a prototype holographic display, we demonstrate how the progress of recent state-of-the-art Neural Holography algorithms can produce high-quality dynamic 3D holograms with accurate focus cues. The advances demonstrated in this work aim to provide a glimpse into a future where our displays can fully reproduce three-dimensional virtual content.

9 August 2025
Verified
Conference Paper
Open access
RKRyota Koiso
Ryota Koiso
SCSuyeon Choi
Suyeon Choi
MGManu Gopakumar
Manu Gopakumar
BCBrian Chao
Brian Chao
JYJacqueline Yang
Jacqueline Yang
GWGordon Wetzstein
Gordon Wetzstein

13 July 2024
Verified
Conference Paper
Open access
SNSeung-Woo Nam
Seung-Woo Nam
DKDongyeon Kim
Dongyeon Kim
SCSuyeon Choi
Suyeon Choi
JLJuhyun Lee
Juhyun Lee
SLSiwoo Lee
Siwoo Lee
YJYoonchan Jeong
Yoonchan Jeong
Cutting-edge computer-generated holography (CGH) algorithms have realized significant advancements in reconstructing the desired light field, enabling the creation of 4D light field holograms. These holograms offer view-dependent effects, such as motion parallax, occlusion, and specular reflections, which are crucial for enhancing the perceptual realism of 3D scenes. Our holographic display prototype leverages sophisticated CGH algorithms in conjunction with a high-speed binary spatial light modulator (SLM) to deliver an immersive experience of 4D light field holograms. This demonstration highlights the latest progress in CGH technology and emphasizes the critical role of parallax cues in providing perceptually realistic 3D contents.