KinD-LCE Curve Estimation And Retinex Fusion On Low-Light Image

Abstract

Low-light images often suffer from noise and color distortion. Object detection, semantic segmentation, instance segmentation, and other tasks are challenging when working with low-light images because of image noise and chromatic aberration. We also found that the conventional Retinex theory loses information in adjusting the image for low-light tasks. In response to the aforementioned problem, this paper proposes an algorithm for low illumination enhancement. The proposed method, KinD-LCE, uses a light curve estimation module to enhance the illumination map in the Retinex decomposed image, improving the overall image brightness. An illumination map and reflection map fusion module were also proposed to restore the image details and reduce detail loss. Additionally, a TV(total variation) loss function was applied to eliminate noise. Our method was trained on the GladNet dataset, known for its diverse collection of low-light images, tested against the Low-Light dataset, and evaluated using the ExDark dataset for downstream tasks, demonstrating competitive performance with a PSNR of 19.7216 and SSIM of 0.8213.

Accepted by Signal, Image and Video Processing

References in corpus (8)

• Deep Bilateral Learning for Real-Time Image Enhancement
• A Bio-Inspired Multi-Exposure Fusion Framework for Low-light Image Enhancement
• Zero-Reference Deep Curve Estimation for Low-Light Image Enhancement
• Kindling the Darkness: A Practical Low-light Image Enhancer
• Retinex-inspired Unrolling with Cooperative Prior Architecture Search for Low-light Image Enhancement
• Low-Light Image and Video Enhancement Using Deep Learning: A Survey
• ReLLIE: Deep Reinforcement Learning for Customized Low-Light Image Enhancement
• Enhancing Low-Light Images in Real World via Cross-Image Disentanglement