Guardado en:
| Autor principal: | |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2401.08185 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866911758608760832 |
|---|---|
| author | Wei, Bingcai |
| author_facet | Wei, Bingcai |
| contents | Rainy weather will have a significant impact on the regular operation of the imaging system. Based on this premise, image rain removal has always been a popular branch of low-level visual tasks, especially methods using deep neural networks. However, most neural networks are but-branched, such as only using convolutional neural networks or Transformers, which is unfavourable for the multidimensional fusion of image features. In order to solve this problem, this paper proposes a dual-branch attention fusion network. Firstly, a two-branch network structure is proposed. Secondly, an attention fusion module is proposed to selectively fuse the features extracted by the two branches rather than simply adding them. Finally, complete ablation experiments and sufficient comparison experiments prove the rationality and effectiveness of the proposed method. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_08185 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | DPAFNet:Dual Path Attention Fusion Network for Single Image Deraining Wei, Bingcai Computer Vision and Pattern Recognition Artificial Intelligence Image and Video Processing Rainy weather will have a significant impact on the regular operation of the imaging system. Based on this premise, image rain removal has always been a popular branch of low-level visual tasks, especially methods using deep neural networks. However, most neural networks are but-branched, such as only using convolutional neural networks or Transformers, which is unfavourable for the multidimensional fusion of image features. In order to solve this problem, this paper proposes a dual-branch attention fusion network. Firstly, a two-branch network structure is proposed. Secondly, an attention fusion module is proposed to selectively fuse the features extracted by the two branches rather than simply adding them. Finally, complete ablation experiments and sufficient comparison experiments prove the rationality and effectiveness of the proposed method. |
| title | DPAFNet:Dual Path Attention Fusion Network for Single Image Deraining |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Image and Video Processing |
| url | https://arxiv.org/abs/2401.08185 |