Brian Chao

I'm a 4th year PhD candidate 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.

I work on spatial computing, spanning 3D scene reconstruction and neural rendering, next-generation AR/VR displays, and most recently token efficiency in visual generation for immersive experiences and robotics.

I've spent two summers at Meta Reality Labs, where I worked on neural rendering for 3D reconstruction and next-generation computational AR/VR displays. I've also served as a reviewer for SIGGRAPH, SIGGRAPH Asia, NeurIPS, ISMAR, TIP, TCI, ICIP, and ICASSP.

Email  /  CV  /  Google Scholar  /  Twitter  /  LinkedIn  /  Github

Research

When state-of-the-art neural rendering meets next-generation holographic VR displays: converting optimized Gaussian splats to holograms that support natural focus cues.

Augmenting Gaussians with RGBA texture maps greatly improves novel-view synthesis quality in 3D Gaussian Splatting.

The novel combination of a multisource laser array and a dynamic Fourier amplitude modulator significantly improves holographic VR display étendue and light field hologram image quality.

A near-eye display design that pairs inverse-designed metasurface waveguides with AI-driven holographic displays to enable full-colour 3D augmented reality from a compact glasses-like form factor.

The inclusion of parallax cues in CGH rendering plays a crucial role in enhancing perceptual realism, and we show this through a live demonstration of 4D light field holograms.

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

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

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

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

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

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

Industry Experiences

Website source code from here.