IAML：用于低光图像增强自编码器的渐进学习中的 illumination-aware mirror loss
摘要
本 letter 提出一种新的训练方法和损失函数，用于学习低光图像增强自编码器。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.
引用
@article{arxiv.2603.13363,
title = {IAML: Illumination-Aware Mirror Loss for Progressive Learning in Low-Light Image Enhancement Auto-encoders},
author = {Farida Mohsen and Tala Zaim and Ali Al-Zawqari and Ali Safa and Samir Belhaouari},
journal= {arXiv preprint arXiv:2603.13363},
year = {2026}
}