Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2604.25367 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913075149406208 |
|---|---|
| author | Wen, Jianyu Xie, Jun Chen, Feng Wang, Zhepeng Wu, Chenhao Zhang, Tong Yu, Yixuan Swierczynski, Piotr |
| author_facet | Wen, Jianyu Xie, Jun Chen, Feng Wang, Zhepeng Wu, Chenhao Zhang, Tong Yu, Yixuan Swierczynski, Piotr |
| contents | In this paper, we present Self-DACE++, an improved unsupervised and lightweight framework for Low-Light Image Enhancement (LLIE), building upon our previous Self-Reference Deep Adaptive Curve Estimation (Self-DACE). To better address the trade-off between computational efficiency and restoration quality, Self-DACE++ introduces enhanced Adaptive Adjustment Curves (AACs). These curves, governed by minimal trainable parameters, flexibly adjust the dynamic range while preserving the color fidelity, structural integrity, and naturalness of the enhanced images. To achieve an extremely lightweight architecture without sacrificing performance, we propose a randomized order training strategy coupled with a network fusion mechanism, which compresses the model into an efficient iterative inference structure. Furthermore, we formulate a physics-grounded objective function based on Retinex theory and incorporate a dedicated denoising module to effectively estimate and suppress latent noise in dark regions. Extensive qualitative and quantitative evaluations on multiple real-world benchmark datasets demonstrate that Self-DACE++ outperforms existing state-of-the-art methods, delivering superior enhancement quality with real-time inference capability. The code is available at https://github.com/John-Wendell/Self-DACE. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_25367 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Self-DACE++: Robust Low-Light Enhancement via Efficient Adaptive Curve Estimation Wen, Jianyu Xie, Jun Chen, Feng Wang, Zhepeng Wu, Chenhao Zhang, Tong Yu, Yixuan Swierczynski, Piotr Computer Vision and Pattern Recognition In this paper, we present Self-DACE++, an improved unsupervised and lightweight framework for Low-Light Image Enhancement (LLIE), building upon our previous Self-Reference Deep Adaptive Curve Estimation (Self-DACE). To better address the trade-off between computational efficiency and restoration quality, Self-DACE++ introduces enhanced Adaptive Adjustment Curves (AACs). These curves, governed by minimal trainable parameters, flexibly adjust the dynamic range while preserving the color fidelity, structural integrity, and naturalness of the enhanced images. To achieve an extremely lightweight architecture without sacrificing performance, we propose a randomized order training strategy coupled with a network fusion mechanism, which compresses the model into an efficient iterative inference structure. Furthermore, we formulate a physics-grounded objective function based on Retinex theory and incorporate a dedicated denoising module to effectively estimate and suppress latent noise in dark regions. Extensive qualitative and quantitative evaluations on multiple real-world benchmark datasets demonstrate that Self-DACE++ outperforms existing state-of-the-art methods, delivering superior enhancement quality with real-time inference capability. The code is available at https://github.com/John-Wendell/Self-DACE. |
| title | Self-DACE++: Robust Low-Light Enhancement via Efficient Adaptive Curve Estimation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2604.25367 |