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.
翻译:低光视觉由于严重的照明退化,仍然是计算机视觉中的一个基本挑战,这显著影响检测和分割等下游任务的性能。尽管当前最先进的方法通过不变特征学习模块提升了性能,但由于对低光条件建模不完整,它们仍存在不足。因此,我们重新审视低光图像形成过程,并扩展经典的朗伯模型以更好地表征低光条件。通过将分析转换到频域,我们从理论上证明,可以通过结构化滤波过程利用频域通道比率提取照明不变特征。随后,我们提出一个新颖且可端到端训练的模块,命名为频域径向基网络(FRBNet),该模块将频域通道比率操作与可学习的频域滤波器相结合,以实现整体照明不变特征的增强。作为一个即插即用模块,FRBNet无需修改损失函数即可集成到现有网络中,用于低光下游任务。在各种下游任务上的大量实验表明,FRBNet实现了卓越的性能,包括在暗光物体检测中提升+2.2 mAP,在夜间分割中提升+2.9 mIoU。代码发布于:https://github.com/Sing-Forevet/FRBNet。