Rethinking Theoretical Illumination for Efficient Low-Light Image Enhancement
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866913981347659776 |
|---|---|
| author | Weng, Shyang-En Hsiao, Cheng-Yen Lu, Li-Wei Huang, Yu-Shen Chen, Tzu-Han Miaou, Shaou-Gang Christanto, Ricky |
| author_facet | Weng, Shyang-En Hsiao, Cheng-Yen Lu, Li-Wei Huang, Yu-Shen Chen, Tzu-Han Miaou, Shaou-Gang Christanto, Ricky |
| contents | Enhancing low-light images remains a critical challenge in computer vision, as does designing lightweight models for edge devices that can handle the computational demands of deep learning. This article introduces an extended version of the Channel-Prior and Gamma-Estimation Network (CPGA-Net), termed CPGA-Net+, incorporating the theoretically-based Attentions for illumination in local and global processing. Additionally, we assess our approach through a theoretical analysis of the block design by introducing both an ultra-lightweight and a stronger version, following the same design principles. The lightweight version significantly reduces computational costs by over two-thirds by utilizing the local branch as an auxiliary component. Meanwhile, the stronger version achieves an impressive balance by maximizing local and global processing capabilities. Our proposed methods have been validated as effective compared to recent lightweight approaches, offering superior performance and scalable solutions with limited computational resources. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_05274 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Rethinking Theoretical Illumination for Efficient Low-Light Image Enhancement Weng, Shyang-En Hsiao, Cheng-Yen Lu, Li-Wei Huang, Yu-Shen Chen, Tzu-Han Miaou, Shaou-Gang Christanto, Ricky Image and Video Processing Computer Vision and Pattern Recognition Enhancing low-light images remains a critical challenge in computer vision, as does designing lightweight models for edge devices that can handle the computational demands of deep learning. This article introduces an extended version of the Channel-Prior and Gamma-Estimation Network (CPGA-Net), termed CPGA-Net+, incorporating the theoretically-based Attentions for illumination in local and global processing. Additionally, we assess our approach through a theoretical analysis of the block design by introducing both an ultra-lightweight and a stronger version, following the same design principles. The lightweight version significantly reduces computational costs by over two-thirds by utilizing the local branch as an auxiliary component. Meanwhile, the stronger version achieves an impressive balance by maximizing local and global processing capabilities. Our proposed methods have been validated as effective compared to recent lightweight approaches, offering superior performance and scalable solutions with limited computational resources. |
| title | Rethinking Theoretical Illumination for Efficient Low-Light Image Enhancement |
| topic | Image and Video Processing Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2409.05274 |