GaSLight: Gaussian Splats for Spatially-Varying Lighting in HDR
This work addresses the challenge of using regular images as light sources in 3D rendering, which is a domain-specific advancement in computer graphics and vision.
The paper tackles the problem of generating spatially-varying lighting from regular images by introducing GaSLight, which uses HDR Gaussian Splats as a light source representation, achieving state-of-the-art results in HDR estimations and applications like illuminating virtual objects.
We present GaSLight, a method that generates spatially-varying lighting from regular images. Our method proposes using HDR Gaussian Splats as light source representation, marking the first time regular images can serve as light sources in a 3D renderer. Our two-stage process first enhances the dynamic range of images plausibly and accurately by leveraging the priors embedded in diffusion models. Next, we employ Gaussian Splats to model 3D lighting, achieving spatially variant lighting. Our approach yields state-of-the-art results on HDR estimations and their applications in illuminating virtual objects and scenes. To facilitate the benchmarking of images as light sources, we introduce a novel dataset of calibrated and unsaturated HDR to evaluate images as light sources. We assess our method using a combination of this novel dataset and an existing dataset from the literature. Project page: https://lvsn.github.io/gaslight/