IAML: Illumination-Aware Mirror Loss for Progressive Learning in Low-Light Image Enhancement Auto-encoders

TL;DR

This paper introduces a novel illumination-aware mirror loss (IAML) for training low-light image enhancement auto-encoders, improving feature alignment and achieving state-of-the-art results across multiple datasets.

Contribution

The paper proposes a new loss function, IAML, that enhances progressive learning in auto-encoders by considering lighting variations, which is a novel approach in low-light image enhancement.

Findings

Achieves state-of-the-art SSIM, PSNR, LPIPS metrics

Demonstrates the effectiveness of IAML through ablation studies

Outperforms existing methods on three benchmark datasets

Abstract

This letter presents a novel training approach and loss function for learning low-light image enhancement auto-encoders. Our approach revolves around the use of a teacher-student auto-encoder setup coupled to a progressive learning approach where multi-scale information from clean image decoder feature maps is distilled into each layer of the student decoder in a mirrored fashion using a newly-proposed loss function termed Illumination-Aware Mirror Loss (IAML). IAML helps aligning the feature maps within the student decoder network with clean feature maps originating from the teacher side while taking into account the effect of lighting variations within the input images. Extensive benchmarking of our proposed approach on three popular low-light image enhancement datasets demonstrate that our model achieves state-of-the-art performance in terms of average SSIM, PSNR and LPIPS reconstruction accuracy metrics. Finally, ablation studies are performed to clearly demonstrate the effect of IAML on the image reconstruction accuracy.