Bio

I am a Research Scientist at NVIDIA Real-Time Graphics Research group, primarily working on physically-based rendering and neural rendering.
I earned my PhD from University of California San Diego, where I was advised by Professor Ravi Ramamoorthi and worked closely with Professor Tzu-Mao Li. Previously, I obtained my bachelor's degree in CS from the University of Hong Kong and worked on knowledge-based question answering systems with Professor Benjamin Kao.

Prior to PhD, I gained three years of industry experience in photo-realistic rendering (developing our in-house offline renderer FF; the startup just IPO-ed) and 3D designer tools, where my manager Dr. Rui Tang first guided me into graphics research. During PhD, I had the fortune to work with amazing mentors and colleagues at several research teams: Adobe Graphics Research (2022, with Fujun Luan, Miloš Hašan and Iliyan Georgiev), Nvidia Real Time Rendering team (2024-2025, with Marco Salvi), Meta Reality Labs twice (2023, with Carl Marshall and 2025, with Brian Budge).

Research

I am mainly interested in physically-based rendering, neural rendering and real-time graphics, especially forward&inverse light transport simulation, stochastic sampling, learning approaches for appearance modelling and data-prior boosted light transport in general. Recently I'm very interested in optimization problems and 3D geometric learning. Furthermore, I am motivated to create artistic tools to serve the future workflows of artists, helping them realize their own artistic vision and style.

A Generalizable Light Transport 3D Embedding for Global Illumination
Bing Xu, Mukund Varma T, Cheng Wang, Tzu-Mao Li, Lifan Wu, Bart Wronski, Ravi Ramamoorthi, Marco Salvi
ACM SIGGRAPH, 2026
project page / paper / 3D scenes & code (coming)

We learn a scalable 3D embedding with point clouds and linear-complexity transformers to overcome memory bottlenecks, enabling global light transport modeling on millions of triangles. It features resolution-agnostic decoding, a local mechanism with constant per-pixel complexity that ensures view-consistent and generalizable global illumination through 3D supervision.

8DNA: 8D Neural Asset Light Transport by Distribution Learning
Liwen Wu, Haolin Lu, Bing Xu, Miloš Hašan, Ravi Ramamoorthi
ACM SIGGRAPH, 2026
project page / paper

We introduce 8D neural assets to pre-bake complex global illumination effects such as subsurface scattering and glossy interreflections into neural representations. Unlike prior methods that assume far-field lighting and precompute light transport into 6D functions, 8DNA learns the full 8D light transport, enabling accurate rendering under near-field illumination.

Residual Path Integrals for Re-Rendering
Bing Xu, Tzu-Mao Li, Iliyan Georgiev, Trevor Hedstrom, Ravi Ramamoorthi
Computer Graphics Forum (Proceedings of Eurographics Symposium on Rendering), 2024
Best Paper Award
project page / paper / slides / code (coming)

Incremental re-rendering of scenes in a common scenario where only a small portion is moving or edited (e.g. the main character hanging around in an open world). Formulating the difference between two frames as a (correlated) light-transport integral. Devising sampling strategies to focus on paths with non-zero residual-radiance contribution and tailoring appropriate path mappings.
We welcome increased attention to the exploration and potential optimization of the residual path integral and, overall, the re-rendering problem. It is by essence a finite difference renderer and I'm also interested in exploring its applications in inverse rendering.

BSDF Importance Sampling using a Diffusion Model
Ziyang Fu, Yash Belhe, Haolin Lu, Liwen Wu, Bing Xu, Tzu-Mao Li
ACM SIGGRAPH Asia, 2024
project page / paper / code

BSDF importance sampling, using compact diffusion models to represent spherical domain probability density distributions.

Neusample: Importance Sampling for Neural Materials
Bing Xu, Liwen Wu, Miloš Hašan, Fujun Luan, Iliyan Georgiev, Zexiang Xu, Ravi Ramamoorthi
ACM SIGGRAPH, 2023
project page / paper / code

A simple toolbox composed of three approaches to efficiently importance sample neural SVBRDFs, potentially facilitating the broader adoption of neural material models in production.

Importance Sampling BRDF Derivatives
Yash Belhe, Bing Xu, Sai Praveen Bangaru, Ravi Ramamoorthi, Tzu-Mao Li
ACM Transactions on Graphics (TOG), 2024
project page / paper

Importance sampling real-valued derivatives, enabling better recovery of spatially varying textures through GD-based inverse rendering.

Adversarial Monte Carlo Denoising with Conditioned Auxiliary Feature Modulation
Bing Xu, Junfei Zhang, Rui Wang, Kun Xu, Yong-liang Yang, Chuan Li, Rui Tang
ACM Transactions on Graphics (TOG), ACM SIGGRAPH Asia, 2019
project page / paper / code

Denoising Monte Carlo renderings by better utilizing the first bounce auxiliary features and adversarial loss.

Art

→ View Gallery

I am a painter and currently an associate member of the Puget Sound Group Northwest Artists. I mostly paint landscapes in the PNW and California, but also sketch random thoughts and emotions. Oil paint is my favorite medium, and I use acrylics or soft pastels for quick sketches. Some of my work can be found in the gallery above. These photos were taken casually, so the resolution may not be good. Perhaps I will get more serious about it once my paintings start making money. You know, the best-case scenario I can think of: after the painter's death.

I have always been a visual person and am born sensitive to colors. Expressing and communicating via pixels are my choice of words. Painting is one form, ray tracing is another.

Miscellany

I used to play some soccer with our community amateur team when the sun was not too bright (what does this mean in San Diego?). Now, sadly, I am slightly too old for that level of intensity.