cs.CVNov 9, 2026

RetinexGS: Retinex-Inspired Gaussian Splatting for Low-Light RAW Reconstruction

Authors: Yulang Fei, Huaiyuan Weng, Chul Min Yeum

Organizations: University of Waterloo Waterloo, Ontario, Canada

Abstract

Standard 3D Gaussian Splatting (3DGS) pipelines struggle with severely underexposed images, producing unstable colors, floating artifacts, and incomplete reconstructions in dark regions. To better account for noise in these low-light observations, RAW images offer a natural basis for noise-aware reconstruction by preserving linear sensor measurements and providing access to noise metadata. We present RetinexGS, a RAW-domain 3DGS framework that combines Retinex-inspired appearance modeling with sensor-informed optimization for low-light novel-view synthesis. We factorize each Gaussian's color into a view-independent base color and a shared, position- and view-dependent modulation field, regularizing the two components separately to constrain appearance learning from noisy observations. We use DNG noise metadata to weight the reconstruction loss for signal-dependent noise, while distortion-aware rendering avoids spatially resampling RAW targets. To address sparse geometry in dark regions, we introduce depth-guided initialization. We evaluate RetinexGS on three public RawNeRF scenes and two custom-captured low-light RAW scenes. With all methods trained on the same RAW inputs for each scene, RetinexGS outperforms LE3D and RawNeRF in mean sRGB PSNR by 2.18 dB and 2.71 dB respectively, across the five scenes, while supporting real-time novel-view rendering.

Figures & tables

Appendix figures & tables11 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Light 'em Up: Enabling Few-Shot Low-Light 3D Gaussian Splatting with Multi-Scale Explicit Retinex Illumination Decoupling

    Apr 27, 2026YuHao Yin, Zongji Wang, Yuanben Zhang +3Multi-View Consistency3D Gaussian Splatting

  2. DelowlightSplat: Feed-Forward Gaussian Splatting for Lowlight 3D Scene Reconstruction

    May 26, 2026Fuzhen Jiang, Zengtian Xie, Zhuoran Li3D Gaussian Splatting3D Reconstruction

  3. NOVA-GS: Noise-Aware View-Consistent Gaussian Splatting for Low-Light Novel View Synthesis

    Sep 11, 2026Shaurya Pavan A, Vemunuri Divya Madhuri, Yash Pradeep Gawande +1Multi-View Consistency3D Gaussian Splatting