Edge-guided Low-light Image Enhancement with Inertial Bregman Alternating Linearized Minimization
Fuente:
arXiv
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866908468795932672 |
|---|---|
| author | Huang, Chaoyan Wu, Zhongming Zeng, Tieyong |
| author_facet | Huang, Chaoyan Wu, Zhongming Zeng, Tieyong |
| contents | Prior-based methods for low-light image enhancement often face challenges in extracting available prior information from dim images. To overcome this limitation, we introduce a simple yet effective Retinex model with the proposed edge extraction prior. More specifically, we design an edge extraction network to capture the fine edge features from the low-light image directly. Building upon the Retinex theory, we decompose the low-light image into its illumination and reflectance components and introduce an edge-guided Retinex model for enhancing low-light images. To solve the proposed model, we propose a novel inertial Bregman alternating linearized minimization algorithm. This algorithm addresses the optimization problem associated with the edge-guided Retinex model, enabling effective enhancement of low-light images. Through rigorous theoretical analysis, we establish the convergence properties of the algorithm. Besides, we prove that the proposed algorithm converges to a stationary point of the problem through nonconvex optimization theory. Furthermore, extensive experiments are conducted on multiple real-world low-light image datasets to demonstrate the efficiency and superiority of the proposed scheme. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_01142 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Edge-guided Low-light Image Enhancement with Inertial Bregman Alternating Linearized Minimization Huang, Chaoyan Wu, Zhongming Zeng, Tieyong Computer Vision and Pattern Recognition Numerical Analysis 65K05, 65K15, 94A08 Prior-based methods for low-light image enhancement often face challenges in extracting available prior information from dim images. To overcome this limitation, we introduce a simple yet effective Retinex model with the proposed edge extraction prior. More specifically, we design an edge extraction network to capture the fine edge features from the low-light image directly. Building upon the Retinex theory, we decompose the low-light image into its illumination and reflectance components and introduce an edge-guided Retinex model for enhancing low-light images. To solve the proposed model, we propose a novel inertial Bregman alternating linearized minimization algorithm. This algorithm addresses the optimization problem associated with the edge-guided Retinex model, enabling effective enhancement of low-light images. Through rigorous theoretical analysis, we establish the convergence properties of the algorithm. Besides, we prove that the proposed algorithm converges to a stationary point of the problem through nonconvex optimization theory. Furthermore, extensive experiments are conducted on multiple real-world low-light image datasets to demonstrate the efficiency and superiority of the proposed scheme. |
| title | Edge-guided Low-light Image Enhancement with Inertial Bregman Alternating Linearized Minimization |
| topic | Computer Vision and Pattern Recognition Numerical Analysis 65K05, 65K15, 94A08 |
| url | https://arxiv.org/abs/2403.01142 |