AI Paper Atlas

Research map / 3D vision / Gaussian splatting

GaSLight: Gaussian Splats for Spatially-Varying Lighting in HDR

Christophe Bolduc, Yannick Hold-Geoffroy, Jean-François Lalonde

ICCV 2025 · 3D vision › Gaussian splatting · approach: Regularization and primitive design for 3DGS · 7 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use diffusion-based multi-exposure HDR estimator instead of LaNet within the Gaussian splat pipeline (ablation)GaSLight · PanoHDR-NeRF Chess roomRelight PSNR: 23.00 -> 30.50Improved
replace NeRF/LANet lighting with HDR Gaussian splats plus diffusion HDR estimationGaSLight vs PanoHDR-NeRF · PanoHDR-NeRF Chess roomRelight MSE: 0.0134 -> 0.0026Improved
use GaSLight HDR estimator versus prior LDR-to-HDR methodsGaSLight · Si-HDR (113 unsaturated)Relight MSE: 0.0178 -> 0.0131 (vs SingleHDR)Improved
GaSLight versus prior LDR-to-HDR methods on BtP-HDRGaSLight · BtP-HDRRelight PSNR: best MSE 0.0041, but PSNR 28.7022 vs MaskHDR 30.9510Mixed
general (non-category-specific) network versus GlowGAN trained on landscapesGaSLight · Si-HDR landscape subset (23 images)Relight PSNR: 23.82 -> 25.05Improved
reconstruct HDR 3DGS with spherical harmonics colors on inconsistent per-image HDR predictions (ablation)GaSLight · multi-view consistency (qualitative)multi-view consistencyImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy