GaSLight: Gaussian Splats for Spatially-Varying Lighting in HDR

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Bolduc, Christophe, Hold-Geoffroy, Yannick, Shu, Zhixin, Lalonde, Jean-François
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914100269809664
author Bolduc, Christophe
Hold-Geoffroy, Yannick
Shu, Zhixin
Lalonde, Jean-François
author_facet Bolduc, Christophe
Hold-Geoffroy, Yannick
Shu, Zhixin
Lalonde, Jean-François
contents 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/
format Preprint
id arxiv_https___arxiv_org_abs_2504_10809
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle GaSLight: Gaussian Splats for Spatially-Varying Lighting in HDR
Bolduc, Christophe
Hold-Geoffroy, Yannick
Shu, Zhixin
Lalonde, Jean-François
Computer Vision and Pattern Recognition
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/
title GaSLight: Gaussian Splats for Spatially-Varying Lighting in HDR
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2504.10809