URetinex-Net : Retinex-based Deep Unfolding Network for Low-light Image Enhancement
Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review
Author(s)
Related Research Unit(s)
Detail(s)
Original language | English |
---|---|
Title of host publication | Proceedings - 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition |
Subtitle of host publication | CVPR 2022 |
Publisher | Institute of Electrical and Electronics Engineers, Inc. |
Pages | 5891-5900 |
ISBN (electronic) | 9781665469463 |
ISBN (print) | 978-1-6654-6947-0 |
Publication status | Published - 2022 |
Publication series
Name | Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition |
---|---|
ISSN (Print) | 1063-6919 |
ISSN (electronic) | 2575-7075 |
Conference
Title | 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2022) |
---|---|
Location | Hybrid |
Place | United States |
City | New Orleans |
Period | 19 - 24 June 2022 |
Link(s)
Abstract
Retinex model-based methods have shown to be effective in layer-wise manipulation with well-designed priors for low-light image enhancement. However, the commonly used handcrafted priors and optimization-driven solutions lead to the absence of adaptivity and efficiency. To address these issues, in this paper, we propose a Retinex-based deep unfolding network (URetinex-Net), which unfolds an optimization problem into a learnable network to decompose a low-light image into reflectance and illumination layers. By formulating the decomposition problem as an implicit priors regularized model, three learning-based modules are carefully designed, responsible for data-dependent initialization, high-efficient unfolding optimization, and user-specified illumination enhancement, respectively. Particularly, the proposed unfolding optimization module, introducing two networks to adaptively fit implicit priors in data-driven manner, can realize noise suppression and details preservation for the final decomposition results. Extensive experiments on real-world low-light images qualitatively and quantitatively demonstrate the effectiveness and superiority of the proposed method over state-of-the-art methods. The code is available at https://github.com/AndersonYong/URetinex-Net.
Research Area(s)
- Low-level vision
Citation Format(s)
URetinex-Net: Retinex-based Deep Unfolding Network for Low-light Image Enhancement. / Wu, Wenhui; Weng, Jian; Zhang, Pingping et al.
Proceedings - 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition: CVPR 2022. Institute of Electrical and Electronics Engineers, Inc., 2022. p. 5891-5900 (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition).
Proceedings - 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition: CVPR 2022. Institute of Electrical and Electronics Engineers, Inc., 2022. p. 5891-5900 (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition).
Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review