Illuminating Darkness: Learning to Enhance Low-light Images In-the-Wild
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866917174681010176 |
|---|---|
| author | Sharif, S M A Rehman, Abdur Abidin, Zain Ul Dharejo, Fayaz Ali Timofte, Radu Naqvi, Rizwan Ali |
| author_facet | Sharif, S M A Rehman, Abdur Abidin, Zain Ul Dharejo, Fayaz Ali Timofte, Radu Naqvi, Rizwan Ali |
| contents | Single-shot low-light image enhancement (SLLIE) remains challenging due to the limited availability of diverse, real-world paired datasets. To bridge this gap, we introduce the Low-Light Smartphone Dataset (LSD), a large-scale, high-resolution (4K+) dataset collected in the wild across a wide range of challenging lighting conditions (0.1 to 200 lux). LSD contains 6,425 precisely aligned low and normal-light image pairs, selected from over 8,000 dynamic indoor and outdoor scenes through multi-frame acquisition and expert evaluation. To evaluate generalization and aesthetic quality, we collect 2,117 unpaired low-light images from previously unseen devices. To fully exploit LSD, we propose TFFormer, a hybrid model that encodes luminance and chrominance (LC) separately to reduce color-structure entanglement. We further propose a cross-attention-driven joint decoder for context-aware fusion of LC representations, along with LC refinement and LC-guided supervision to significantly enhance perceptual fidelity and structural consistency. TFFormer achieves state-of-the-art results on LSD (+2.45 dB PSNR) and substantially improves downstream vision tasks, such as low-light object detection (+6.80 mAP on ExDark). |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_06898 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Illuminating Darkness: Learning to Enhance Low-light Images In-the-Wild Sharif, S M A Rehman, Abdur Abidin, Zain Ul Dharejo, Fayaz Ali Timofte, Radu Naqvi, Rizwan Ali Computer Vision and Pattern Recognition Single-shot low-light image enhancement (SLLIE) remains challenging due to the limited availability of diverse, real-world paired datasets. To bridge this gap, we introduce the Low-Light Smartphone Dataset (LSD), a large-scale, high-resolution (4K+) dataset collected in the wild across a wide range of challenging lighting conditions (0.1 to 200 lux). LSD contains 6,425 precisely aligned low and normal-light image pairs, selected from over 8,000 dynamic indoor and outdoor scenes through multi-frame acquisition and expert evaluation. To evaluate generalization and aesthetic quality, we collect 2,117 unpaired low-light images from previously unseen devices. To fully exploit LSD, we propose TFFormer, a hybrid model that encodes luminance and chrominance (LC) separately to reduce color-structure entanglement. We further propose a cross-attention-driven joint decoder for context-aware fusion of LC representations, along with LC refinement and LC-guided supervision to significantly enhance perceptual fidelity and structural consistency. TFFormer achieves state-of-the-art results on LSD (+2.45 dB PSNR) and substantially improves downstream vision tasks, such as low-light object detection (+6.80 mAP on ExDark). |
| title | Illuminating Darkness: Learning to Enhance Low-light Images In-the-Wild |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2503.06898 |