{"ID":2849694,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.23444","arxiv_id":"2510.23444","title":"FRBNet: Revisiting Low-Light Vision through Frequency-Domain Radial Basis Network","abstract":"Low-light vision remains a fundamental challenge in computer vision due to severe illumination degradation, which significantly affects the performance of downstream tasks such as detection and segmentation. While recent state-of-the-art methods have improved performance through invariant feature learning modules, they still fall short due to incomplete modeling of low-light conditions. Therefore, we revisit low-light image formation and extend the classical Lambertian model to better characterize low-light conditions. By shifting our analysis to the frequency domain, we theoretically prove that the frequency-domain channel ratio can be leveraged to extract illumination-invariant features via a structured filtering process. We then propose a novel and end-to-end trainable module named \\textbf{F}requency-domain \\textbf{R}adial \\textbf{B}asis \\textbf{Net}work (\\textbf{FRBNet}), which integrates the frequency-domain channel ratio operation with a learnable frequency domain filter for the overall illumination-invariant feature enhancement. As a plug-and-play module, FRBNet can be integrated into existing networks for low-light downstream tasks without modifying loss functions. Extensive experiments across various downstream tasks demonstrate that FRBNet achieves superior performance, including +2.2 mAP for dark object detection and +2.9 mIoU for nighttime segmentation. Code is available at: https://github.com/Sing-Forevet/FRBNet.","short_abstract":"Low-light vision remains a fundamental challenge in computer vision due to severe illumination degradation, which significantly affects the performance of downstream tasks such as detection and segmentation. While recent state-of-the-art methods have improved performance through invariant feature learning modules, they...","url_abs":"https://arxiv.org/abs/2510.23444","url_pdf":"https://arxiv.org/pdf/2510.23444v2","authors":"[\"Fangtong Sun\",\"Congyu Li\",\"Ke Yang\",\"Yuchen Pan\",\"Hanwen Yu\",\"Xichuan Zhang\",\"Yiying Li\"]","published":"2025-10-27T15:46:07Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.AI\"]","methods":"[]","has_code":false,"code_links":[{"ID":607732,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2849694,"paper_url":"https://arxiv.org/abs/2510.23444","paper_title":"FRBNet: Revisiting Low-Light Vision through Frequency-Domain Radial Basis Network","repo_url":"https://github.com/Sing-Forevet/FRBNet","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}