paper-with-me

홈 › Papers

DMFourLLIE: Dual-Stage and Multi-Branch Fourier Network for Low-Light Image Enhancement

2024-12-01 · Tongshun Zhang, Pingping Liu, Ming Zhao, Haotian Lv

In the Fourier frequency domain, luminance information is primarily encoded in the amplitude component, while spatial structure information is significantly contained within the phase component. Existing low-light image enhancement techniques using Fourier transform have mainly focused on amplifying the amplitude component and simply replicating the phase component, an approach that often leads to color distortions and noise issues. In this paper, we propose a Dual-Stage Multi-Branch Fourier Low-Light Image Enhancement (DMFourLLIE) framework to address these limitations by emphasizing the phase component's role in preserving image structure and detail. The first stage integrates structural information from infrared images to enhance the phase component and employs a luminance-attention mechanism in the luminance-chrominance color space to precisely control amplitude enhancement. The second stage combines multi-scale and Fourier convolutional branches for robust image reconstruction, effectively recovering spatial structures and textures. This dual-branch joint optimization process ensures that complex image information is retained, overcoming the limitations of previous methods that neglected the interplay between amplitude and phase. Extensive experiments across multiple datasets demonstrate that DMFourLLIE outperforms current state-of-the-art methods in low-light image enhancement. Our code is available at https://github.com/bywlzts/DMFourLLIE.

📄 PDF Abstract BibTeX arXiv:2412.00683

Code (1)

bywlzts/dmfourllie 공식 구현 pytorch

Tasks

Image EnhancementImage ReconstructionLow-Light Image Enhancement

Similar Papers 제목 키워드 기반

Mitigating Frequency Learning Bias in Quantum Models via Multi-Stage Residual Learning

2026-03-10 · Ammar Daskin arxiv

Quantum machine learning models based on parameterized circuits can be viewed as Fourier series approximators. However, they often struggle to learn functions with multiple frequency components, particularly high-frequen…

Quantum Machine Learning

Freq-DP Net: A Dual-Branch Network for Fence Removal using Dual-Pixel and Fourier Priors

2026-02-15 · Kunal Swami, Sudha Velusamy, Chandra Sekhar Seelamantula arxiv

Removing fence occlusions from single images is a challenging task that degrades visual quality and limits downstream computer vision applications. Existing methods often fail on static scenes or require motion cues from…

Globally Optimal Rigid Intensity Based Registration: A Fast Fourier Domain Approach

2016-06-01 · CVPR 2016 6 · Behrooz Nasihatkon, Frida Fejne, Fredrik Kahl

High computational cost is the main obstacle to adapting globally optimal branch-and-bound algorithms to intensity-based registration. Existing techniques to speed up such algorithms use a multiresolution pyramid of imag…

Attention based Dual-Branch Complex Feature Fusion Network for Hyperspectral Image Classification

2023-11-02 · Mohammed Q. Alkhatib, Mina Al-Saad, Nour Aburaed, M. Sami Zitouni 외

This research work presents a novel dual-branch model for hyperspectral image classification that combines two streams: one for processing standard hyperspectral patches using Real-Valued Neural Network (RVNN) and the ot…

Hyperspectral Image Classificationimage-classificationImage Classification

SpecXNet: A Dual-Domain Convolutional Network for Robust Deepfake Detection

2025-09-26 · Inzamamul Alam, Md Tanvir Islam, Simon S. Woo arxiv

The increasing realism of content generated by GANs and diffusion models has made deepfake detection significantly more challenging. Existing approaches often focus solely on spatial or frequency-domain features, limitin…

DeepFake Detection