IAML: Illumination-Aware Mirror Loss for Progressive Learning in Low-Light Image Enhancement Auto-encoders
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912965757763584 |
|---|---|
| author | Mohsen, Farida Zaim, Tala Al-Zawqari, Ali Safa, Ali Belhaouari, Samir |
| author_facet | Mohsen, Farida Zaim, Tala Al-Zawqari, Ali Safa, Ali Belhaouari, Samir |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_13363 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | IAML: Illumination-Aware Mirror Loss for Progressive Learning in Low-Light Image Enhancement Auto-encoders Mohsen, Farida Zaim, Tala Al-Zawqari, Ali Safa, Ali Belhaouari, Samir Computer Vision and Pattern Recognition Artificial Intelligence 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. |
| title | IAML: Illumination-Aware Mirror Loss for Progressive Learning in Low-Light Image Enhancement Auto-encoders |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2603.13363 |