FRBNet: Revisiting Low-Light Vision through Frequency-Domain Radial Basis Network

• URL: http://arxiv.org/abs/2510.23444v2
• Date: Tue, 28 Oct 2025 10:58:40 GMT
• Title: FRBNet: Revisiting Low-Light Vision through Frequency-Domain Radial Basis Network
• Authors: Fangtong Sun, Congyu Li, Ke Yang, Yuchen Pan, Hanwen Yu, Xichuan Zhang, Yiying Li,
• Abstract summary: We revisit low-light image formation and extend the classical Lambertian model to better characterize low-light conditions.<n>We propose a novel and end-to-end trainable module named textbfFrequency-domain textbfRadial textbfBasis textbfNetwork.<n>As a plug-and-play module, FRBNet can be integrated into existing networks for low-light downstream tasks without modifying loss functions.
• Score: 7.386546521017689
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• GTFMN: Guided Texture and Feature Modulation Network for Low-Light Image Enhancement and Super-Resolution [6.392781152715588]
  Low-light image super-resolution (LLSR) is a challenging task due to the degradation coupled with poor illumination.<n>We propose the Guided Texture and Feature Modulation Network (GTFMN), a novel framework that decouples the LLSR task into two sub-problems: illumination estimation and texture restoration.<n>GTFMN achieves the best performance among competing methods on the OmniNormal5 and OmniNormal15 datasets, outperforming them in both quantitative metrics and visual quality.
  arXiv  Detail & Related papers  (2026-01-27T03:43:39Z)
• Revisiting Lightweight Low-Light Image Enhancement: From a YUV Color Space Perspective [17.507319835166406]
  We propose a novel YUV-based paradigm that strategically restores channels using a Dual-Stream Global-Local Attention module for the Y channel, a Y-guided Local-Aware Frequency Attention module for the UV channels, and a Guided Interaction module for final feature fusion.<n>Our model establishes a new state-of-the-art on multiple benchmarks, delivering superior visual quality with a significantly lower parameter count.
  arXiv  Detail & Related papers  (2026-01-24T07:27:54Z)
• DFDNet: Dynamic Frequency-Guided De-Flare Network [8.713784455593778]
  This paper presents a novel dynamic frequency-guided deflare network (DFDNet) that decouples content information from flare artifacts in the frequency domain.<n>The experimental results demonstrate that the proposed method outperforms existing state-of-the-art methods in terms of performance.
  arXiv  Detail & Related papers  (2025-07-23T13:14:59Z)
• Lightweight Federated Learning over Wireless Edge Networks [83.4818741890634]
  Federated (FL) is an alternative at network edge, but an alternative in wireless networks.<n>We derive a closed-form expression FL convergence gap transmission power, model pruning error, and quantization.<n> LTFL outperforms state-the-art schemes in experiments on real-world datasets.
  arXiv  Detail & Related papers  (2025-07-13T09:14:17Z)
• FADPNet: Frequency-Aware Dual-Path Network for Face Super-Resolution [70.61549422952193]
  Face super-resolution (FSR) under limited computational costs remains an open problem.<n>Existing approaches typically treat all facial pixels equally, resulting in suboptimal allocation of computational resources.<n>We propose FADPNet, a Frequency-Aware Dual-Path Network that decomposes facial features into low- and high-frequency components.
  arXiv  Detail & Related papers  (2025-06-17T02:33:42Z)
• Towards Generalized Range-View LiDAR Segmentation in Adverse Weather [65.22588361803942]
  We identify and analyze the unique challenges that affect the generalization of range-view LiDAR segmentation in severe weather.<n>We propose a modular and lightweight framework that enhances robustness without altering the core architecture of existing models.<n>Our approach significantly improves generalization to adverse weather with minimal inference overhead.
  arXiv  Detail & Related papers  (2025-06-10T16:48:27Z)
• WTEFNet: Real-Time Low-Light Object Detection for Advanced Driver Assistance Systems [11.584271733469476]
  WTEFNet is a real-time object detection framework specifically designed for low-light scenarios.<n>WTEFNet comprises three core modules: a Low-Light Enhancement (LLE) module, a Wavelet-based Feature Extraction (WFE) module, and an Adaptive Fusion Detection (AFFD) module.
  arXiv  Detail & Related papers  (2025-05-29T07:36:27Z)
• Rethinking Transformer-Based Blind-Spot Network for Self-Supervised Image Denoising [94.09442506816724]
  Blind-spot networks (BSN) have been prevalent neural architectures in self-supervised image denoising (SSID)<n>We build a Transformer-based Blind-Spot Network (TBSN) which shows strong local fitting and global perspective abilities.
  arXiv  Detail & Related papers  (2024-04-11T15:39:10Z)
• Frequency-Modulated Point Cloud Rendering with Easy Editing [46.299091125921656]
  We develop an effective point cloud rendering pipeline for novel view synthesis. Our pipeline supports real-time rendering and user-friendly editing. In contrast to implicit rendering, our pipeline supports high-fidelity interactive editing based on point cloud manipulation.
  arXiv  Detail & Related papers  (2023-03-14T02:37:11Z)
• Thunder: Thumbnail based Fast Lightweight Image Denoising Network [92.9631117239565]
  A textbfThumbtextbfnail based textbfDtextbfenoising Netwotextbfrk dubbed Thunder is proposed.
  arXiv  Detail & Related papers  (2022-05-24T06:38:46Z)
• Feature Flow: In-network Feature Flow Estimation for Video Object Detection [56.80974623192569]
  Optical flow is widely used in computer vision tasks to provide pixel-level motion information. A common approach is to:forward optical flow to a neural network and fine-tune this network on the task dataset. We propose a novel network (IFF-Net) with an textbfIn-network textbfFeature textbfFlow estimation module for video object detection.
  arXiv  Detail & Related papers  (2020-09-21T07:55:50Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.