Multinex: Lightweight Low-light Image Enhancement via Multi-prior Retinex
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_ | 1866911628896763904 |
|---|---|
| author | Brateanu, Alexandru Mu, Tingting Ancuti, Codruta Ancuti, Cosmin |
| author_facet | Brateanu, Alexandru Mu, Tingting Ancuti, Codruta Ancuti, Cosmin |
| contents | Low-light image enhancement (LLIE) aims to restore natural visibility, color fidelity, and structural detail under severe illumination degradation. State-of-the-art (SOTA) LLIE techniques often rely on large models and multi-stage training, limiting practicality for edge deployment. Moreover, their dependence on a single color space introduces instability and visible exposure or color artifacts. To address these, we propose Multinex, an ultra-lightweight structured framework that integrates multiple fine-grained representations within a principled Retinex residual formulation. It decomposes an image into illumination and color prior stacks derived from distinct analytic representations, and learns to fuse these representations into luminance and reflectance adjustments required to correct exposure. By prioritizing enhancement over reconstruction and exploiting lightweight neural operations, Multinex significantly reduces computational cost, exemplified by its lightweight (45K parameters) and nano (0.7K parameters) versions. Extensive benchmarks show that all lightweight variants significantly outperform their corresponding lightweight SOTA models, and reach comparable performance to heavy models. Paper page available at https://albrateanu.github.io/multinex. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_10359 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Multinex: Lightweight Low-light Image Enhancement via Multi-prior Retinex Brateanu, Alexandru Mu, Tingting Ancuti, Codruta Ancuti, Cosmin Computer Vision and Pattern Recognition Artificial Intelligence Low-light image enhancement (LLIE) aims to restore natural visibility, color fidelity, and structural detail under severe illumination degradation. State-of-the-art (SOTA) LLIE techniques often rely on large models and multi-stage training, limiting practicality for edge deployment. Moreover, their dependence on a single color space introduces instability and visible exposure or color artifacts. To address these, we propose Multinex, an ultra-lightweight structured framework that integrates multiple fine-grained representations within a principled Retinex residual formulation. It decomposes an image into illumination and color prior stacks derived from distinct analytic representations, and learns to fuse these representations into luminance and reflectance adjustments required to correct exposure. By prioritizing enhancement over reconstruction and exploiting lightweight neural operations, Multinex significantly reduces computational cost, exemplified by its lightweight (45K parameters) and nano (0.7K parameters) versions. Extensive benchmarks show that all lightweight variants significantly outperform their corresponding lightweight SOTA models, and reach comparable performance to heavy models. Paper page available at https://albrateanu.github.io/multinex. |
| title | Multinex: Lightweight Low-light Image Enhancement via Multi-prior Retinex |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2604.10359 |