Fast Low-light Enhancement and Deblurring for 3D Dark Scenes
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866914379834851328 |
|---|---|
| author | Zhang, Feng Wang, Jinglong Li, Ze Zhou, Yanghong Chen, Yang Chen, Lei Zhu, Xiatian |
| author_facet | Zhang, Feng Wang, Jinglong Li, Ze Zhou, Yanghong Chen, Yang Chen, Lei Zhu, Xiatian |
| contents | Novel view synthesis from low-light, noisy, and motion-blurred imagery remains a valuable and challenging task. Current volumetric rendering methods struggle with compound degradation, and sequential 2D preprocessing introduces artifacts due to interdependencies. In this work, we introduce FLED-GS, a fast low-light enhancement and deblurring framework that reformulates 3D scene restoration as an alternating cycle of enhancement and reconstruction. Specifically, FLED-GS inserts several intermediate brightness anchors to enable progressive recovery, preventing noise blow-up from harming deblurring or geometry. Each iteration sharpens inputs with an off-the-shelf 2D deblurrer and then performs noise-aware 3DGS reconstruction that estimates and suppresses noise while producing clean priors for the next level. Experiments show FLED-GS outperforms state-of-the-art LuSh-NeRF, achieving 21$\times$ faster training and 11$\times$ faster rendering. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_08133 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Fast Low-light Enhancement and Deblurring for 3D Dark Scenes Zhang, Feng Wang, Jinglong Li, Ze Zhou, Yanghong Chen, Yang Chen, Lei Zhu, Xiatian Computer Vision and Pattern Recognition Novel view synthesis from low-light, noisy, and motion-blurred imagery remains a valuable and challenging task. Current volumetric rendering methods struggle with compound degradation, and sequential 2D preprocessing introduces artifacts due to interdependencies. In this work, we introduce FLED-GS, a fast low-light enhancement and deblurring framework that reformulates 3D scene restoration as an alternating cycle of enhancement and reconstruction. Specifically, FLED-GS inserts several intermediate brightness anchors to enable progressive recovery, preventing noise blow-up from harming deblurring or geometry. Each iteration sharpens inputs with an off-the-shelf 2D deblurrer and then performs noise-aware 3DGS reconstruction that estimates and suppresses noise while producing clean priors for the next level. Experiments show FLED-GS outperforms state-of-the-art LuSh-NeRF, achieving 21$\times$ faster training and 11$\times$ faster rendering. |
| title | Fast Low-light Enhancement and Deblurring for 3D Dark Scenes |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2603.08133 |