Yi-Ruei Liu 劉珆睿

BRDFusion is a unified framework that combines physically based inverse rendering and generative priors for high-quality urban scene inverse rendering and relighting, enabling diverse driving-scene simulations.

We present Skyfall-GS, a framework that synthesizes photorealistic, city-block scale 3D urban scenes from satellite imagery using diffusion models, eliminating the need for expensive 3D scanning and manual annotation while enabling real-time exploration.

We present 4D-GRT, a 4D Gaussian Splatting framework that generates physically accurate camera effects in dynamic scenes via differentiable ray tracing. Our approach combines a two-stage reconstruction pipeline with ray tracing to simulate complex optical effects, providing a robust foundation for camera-aware data generation.

We present SpectroMotion, the first 3D Gaussian Splatting method capable of reconstructing photorealistic dynamic specular scenes. By combining 3DGS with physically-based rendering and deformation fields, we achieve high-quality synthesis of challenging real-world dynamic reflective surfaces.