{"ID":2843059,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.09818","arxiv_id":"2511.09818","title":"Lumos3D: A Single-Forward Framework for Low-Light 3D Scene Restoration","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 will be released soon.","short_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 lo...","url_abs":"https://arxiv.org/abs/2511.09818","url_pdf":"https://arxiv.org/pdf/2511.09818v2","authors":"[\"Hanzhou Liu\",\"Peng Jiang\",\"Jia Huang\",\"Mi Lu\"]","published":"2025-11-12T23:42:03Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false}