cs.CVNov 12, 2025

Lumos3D: A Single-Forward Framework for Low-Light 3D Scene Restoration

Authors: Hanzhou Liu, Peng Jiang, Jia Huang, Mi Lu

Organizations: Texas A&M University, College Station, TX 77801 USA

Abstract

Restoring 3D scenes with low-light conditions is challenging, and most existing methods depend on precomputed camera poses and scene-specific optimization, which greatly restricts their application to real-world scenarios. To overcome these limitations, we propose Lumos3D, a pose-free single-forward framework for 3D low-light scene restoration. First, we develop a cross-illumination distillation scheme, where a frozen teacher network takes normal-light ground truth images as input to distill accurate geometric information to the student model. Second, we define a Lumos loss to improve the restoration quality of the reconstructed 3D Gaussian space. Trained on a single dataset, Lumos3D performs inference in a purely feed-forward manner, directly restoring illumination and structure from unposed, low-light multi-view images without any per-scene training or optimization. Experiments on real-world datasets demonstrate that Lumos3D achieves competitive restoration results compared to scene-specific methods. Our codes are available at https://github.com/HanzhouLiu/Lumos3D.

Figures & tables

Explore similar work

CardsList
  1. Fast Low-light Enhancement and Deblurring for 3D Dark Scenes

    Mar 9, 2026Feng Zhang, Jinglong Wang, Ze Li +4Novel View Synthesis3D Reconstruction

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

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