CVIVAug 6, 2023

FourLLIE: Boosting Low-Light Image Enhancement by Fourier Frequency Information

arXiv:2308.03033v1233 citationsh-index: 16
Originality Incremental advance
AI Analysis

This work addresses image quality issues in low-light conditions for applications like photography and surveillance, representing an incremental improvement over existing Fourier-based methods.

The paper tackles low-light image enhancement by leveraging Fourier frequency information, specifically using amplitude transform maps and SNR maps to improve lightness and recover details, achieving state-of-the-art performance on four datasets with good model efficiency.

Recently, Fourier frequency information has attracted much attention in Low-Light Image Enhancement (LLIE). Some researchers noticed that, in the Fourier space, the lightness degradation mainly exists in the amplitude component and the rest exists in the phase component. By incorporating both the Fourier frequency and the spatial information, these researchers proposed remarkable solutions for LLIE. In this work, we further explore the positive correlation between the magnitude of amplitude and the magnitude of lightness, which can be effectively leveraged to improve the lightness of low-light images in the Fourier space. Moreover, we find that the Fourier transform can extract the global information of the image, and does not introduce massive neural network parameters like Multi-Layer Perceptrons (MLPs) or Transformer. To this end, a two-stage Fourier-based LLIE network (FourLLIE) is proposed. In the first stage, we improve the lightness of low-light images by estimating the amplitude transform map in the Fourier space. In the second stage, we introduce the Signal-to-Noise-Ratio (SNR) map to provide the prior for integrating the global Fourier frequency and the local spatial information, which recovers image details in the spatial space. With this ingenious design, FourLLIE outperforms the existing state-of-the-art (SOTA) LLIE methods on four representative datasets while maintaining good model efficiency.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes