LUMEN: Low-light Unified Multi-stage Enhancement Network using depth-guided flash, clustering, and attention-based Transformers
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866914577323655168 |
|---|---|
| author | Debnath, Bibhabasu Ray, Sahana Ghosh, Sanjay |
| author_facet | Debnath, Bibhabasu Ray, Sahana Ghosh, Sanjay |
| contents | Low-light image enhancement remains a challenging problem due to severe noise, color distortion, contrast degradation, and loss of structural details under insufficient illumination. Existing methods typically apply uniform enhancement without considering the depth-dependent nature of light attenuation and sensor noise in real-world scenes. To address this limitation, we propose LUMEN, a multi-stage enhancement framework that integrates virtual flash simulation with transformer-based feature fusion. The proposed framework first estimates scene depth from low-light inputs using a dedicated encoder-decoder network, after which a soft clustering module partitions pixels into depth-aware regions, enabling depth-dependent flash simulation. The simulated flash features, together with depth representations, are fused with image features through efficient attention-based fusion blocks to enhance global context while preserving fine details. A composite loss function combining reconstruction, perceptual, structural, color, edge, and depth consistency objectives ensures both visual fidelity and perceptual quality. Extensive experiments on LOL-v1 and LOL-v2 benchmarks demonstrate that LUMEN achieves state-of-the-art performance and produces visually natural results compared with several state-of-the-art methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_17893 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | LUMEN: Low-light Unified Multi-stage Enhancement Network using depth-guided flash, clustering, and attention-based Transformers Debnath, Bibhabasu Ray, Sahana Ghosh, Sanjay Image and Video Processing Low-light image enhancement remains a challenging problem due to severe noise, color distortion, contrast degradation, and loss of structural details under insufficient illumination. Existing methods typically apply uniform enhancement without considering the depth-dependent nature of light attenuation and sensor noise in real-world scenes. To address this limitation, we propose LUMEN, a multi-stage enhancement framework that integrates virtual flash simulation with transformer-based feature fusion. The proposed framework first estimates scene depth from low-light inputs using a dedicated encoder-decoder network, after which a soft clustering module partitions pixels into depth-aware regions, enabling depth-dependent flash simulation. The simulated flash features, together with depth representations, are fused with image features through efficient attention-based fusion blocks to enhance global context while preserving fine details. A composite loss function combining reconstruction, perceptual, structural, color, edge, and depth consistency objectives ensures both visual fidelity and perceptual quality. Extensive experiments on LOL-v1 and LOL-v2 benchmarks demonstrate that LUMEN achieves state-of-the-art performance and produces visually natural results compared with several state-of-the-art methods. |
| title | LUMEN: Low-light Unified Multi-stage Enhancement Network using depth-guided flash, clustering, and attention-based Transformers |
| topic | Image and Video Processing |
| url | https://arxiv.org/abs/2605.17893 |