AI RESEARCH
Lumos3D: A Single-Forward Framework for Low-Light 3D Scene Restoration
arXiv CS.CV
•
ArXi:2511.09818v2 Announce Type: replace 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.