Computer vision · Computer graphics
PhD candidate at Université LavalQuébec City, Canada
I am a PhD candidate in computer science at Université Laval, advised by Prof. Jean-François Lalonde in the Computer Vision & Systems Lab. My research focuses on understanding, representing, and manipulating lighting with generative models.
I interned at Adobe Research in London in 2025 and 2026, working on lighting representations and image relighting with Valentin Deschaintre, Iliyan Georgiev, Michael Fischer, Yannick Hold-Geoffroy, Sam Sartor, and Zhixin Shu. My follow-up work explores the editability and controllability of lighting representations.
Previously, I completed my MEng in Computer Technologies at South China University of Technology with Prof. Chuhua Xian, studying consistent depth estimation and BRDF estimation. I also interned as an Unreal Engine developer at Alibaba Lingxi Interactive and as a rendering developer at Revobit, a cloud rendering start-up for the fashion industry. I received my bachelor's degree in E-Commerce from Xidian University.
CVPR 2026 (Highlight)
A joint latent space that unifies multiple lighting representations (environment maps, irradiance, spherical harmonics, text) for cross-modal retrieval, generation, and lighting control.
CIC 33 (Oral)
We propose a white-balanced HDR environment map dataset to evaluate the color robustness of lighting estimation models. We demonstrate that preprocessing inputs with a pre-trained white balance network significantly improves color accuracy without requiring retraining.
3DV 2026
SpotLight enables object relighting by using shadow guidance to control lighting conditions without requiring additional training. Builds upon our previous work ZeroComp.
WACV 2025 (Oral)
Zero-shot 3D object compositing without paired training data. Easily extendable to 2D compositing and material editing.
TMM
An indoor RGB-D dataset with multi-illuminations, and a method for consistent depth estimation under changing lighting.
In a scorching desert, the player discovers an oasis and must lead people to work and survive there.