Enhancing low‐light images with lightweight fused fixed‐directional filters network
Abstract Deep learning has made significant progress in the field of low‐light image enhancement. However, challenges remain, such as the substantial parameter consumption required for effective image enhancement. Inspired by multi‐scale geometric transformations in image detail enhancement, a novel...
Saved in:
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2024-11-01
|
| Series: | IET Image Processing |
| Subjects: | |
| Online Access: | https://doi.org/10.1049/ipr2.13226 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850191392248168448 |
|---|---|
| author | Yang Li |
| author_facet | Yang Li |
| author_sort | Yang Li |
| collection | DOAJ |
| description | Abstract Deep learning has made significant progress in the field of low‐light image enhancement. However, challenges remain, such as the substantial parameter consumption required for effective image enhancement. Inspired by multi‐scale geometric transformations in image detail enhancement, a novel model called the fixed‐directional filters network is proposed. Fixed‐directional filters network takes the original image as input and employs multiple branches for parallel processing. One branch uses conventional convolutional layers to extract features from the original image, while the other branches apply non‐linear mapping layers based on wavelet transforms. These wavelet transform branches capture the multi‐scale information of the image by combining different directions and convolutional kernels and utilize a trainable custom gamma mapping layer for non‐linear modulation to enhance specific regions of the image. The feature maps processed by each branch are merged through concatenation operations and then passed through convolutional layers to output the enhanced image. Using trainable mapping functions alone to enhance details significantly reduces the reliance on convolutional layers, effectively lowering the model's parameter count to only 13k parameters. Additionally, experiments demonstrate that fixed‐directional filters network significantly improves image quality, particularly in capturing image details and enhancing image contrast. |
| format | Article |
| id | doaj-art-0b8f3340ff2d4d318e5117dcc86f4756 |
| institution | OA Journals |
| issn | 1751-9659 1751-9667 |
| language | English |
| publishDate | 2024-11-01 |
| publisher | Wiley |
| record_format | Article |
| series | IET Image Processing |
| spelling | doaj-art-0b8f3340ff2d4d318e5117dcc86f47562025-08-20T02:14:56ZengWileyIET Image Processing1751-96591751-96672024-11-0118133976398810.1049/ipr2.13226Enhancing low‐light images with lightweight fused fixed‐directional filters networkYang Li0School of Computer Science and EngineeringTianjin University of TechnologyTianjinChinaAbstract Deep learning has made significant progress in the field of low‐light image enhancement. However, challenges remain, such as the substantial parameter consumption required for effective image enhancement. Inspired by multi‐scale geometric transformations in image detail enhancement, a novel model called the fixed‐directional filters network is proposed. Fixed‐directional filters network takes the original image as input and employs multiple branches for parallel processing. One branch uses conventional convolutional layers to extract features from the original image, while the other branches apply non‐linear mapping layers based on wavelet transforms. These wavelet transform branches capture the multi‐scale information of the image by combining different directions and convolutional kernels and utilize a trainable custom gamma mapping layer for non‐linear modulation to enhance specific regions of the image. The feature maps processed by each branch are merged through concatenation operations and then passed through convolutional layers to output the enhanced image. Using trainable mapping functions alone to enhance details significantly reduces the reliance on convolutional layers, effectively lowering the model's parameter count to only 13k parameters. Additionally, experiments demonstrate that fixed‐directional filters network significantly improves image quality, particularly in capturing image details and enhancing image contrast.https://doi.org/10.1049/ipr2.13226computer visionimage processing |
| spellingShingle | Yang Li Enhancing low‐light images with lightweight fused fixed‐directional filters network IET Image Processing computer vision image processing |
| title | Enhancing low‐light images with lightweight fused fixed‐directional filters network |
| title_full | Enhancing low‐light images with lightweight fused fixed‐directional filters network |
| title_fullStr | Enhancing low‐light images with lightweight fused fixed‐directional filters network |
| title_full_unstemmed | Enhancing low‐light images with lightweight fused fixed‐directional filters network |
| title_short | Enhancing low‐light images with lightweight fused fixed‐directional filters network |
| title_sort | enhancing low light images with lightweight fused fixed directional filters network |
| topic | computer vision image processing |
| url | https://doi.org/10.1049/ipr2.13226 |
| work_keys_str_mv | AT yangli enhancinglowlightimageswithlightweightfusedfixeddirectionalfiltersnetwork |