Learning Multi-scale Spatial-frequency Features for Image Denoising
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866913903582117888 |
|---|---|
| author | Zhao, Xu Zhao, Chen Hu, Xiantao Zhang, Hongliang Tai, Ying Yang, Jian |
| author_facet | Zhao, Xu Zhao, Chen Hu, Xiantao Zhang, Hongliang Tai, Ying Yang, Jian |
| contents | Recent advancements in multi-scale architectures have demonstrated exceptional performance in image denoising tasks. However, existing architectures mainly depends on a fixed single-input single-output Unet architecture, ignoring the multi-scale representations of pixel level. In addition, previous methods treat the frequency domain uniformly, ignoring the different characteristics of high-frequency and low-frequency noise. In this paper, we propose a novel multi-scale adaptive dual-domain network (MADNet) for image denoising. We use image pyramid inputs to restore noise-free results from low-resolution images. In order to realize the interaction of high-frequency and low-frequency information, we design an adaptive spatial-frequency learning unit (ASFU), where a learnable mask is used to separate the information into high-frequency and low-frequency components. In the skip connections, we design a global feature fusion block to enhance the features at different scales. Extensive experiments on both synthetic and real noisy image datasets verify the effectiveness of MADNet compared with current state-of-the-art denoising approaches. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_16307 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Learning Multi-scale Spatial-frequency Features for Image Denoising Zhao, Xu Zhao, Chen Hu, Xiantao Zhang, Hongliang Tai, Ying Yang, Jian Computer Vision and Pattern Recognition Artificial Intelligence Image and Video Processing Recent advancements in multi-scale architectures have demonstrated exceptional performance in image denoising tasks. However, existing architectures mainly depends on a fixed single-input single-output Unet architecture, ignoring the multi-scale representations of pixel level. In addition, previous methods treat the frequency domain uniformly, ignoring the different characteristics of high-frequency and low-frequency noise. In this paper, we propose a novel multi-scale adaptive dual-domain network (MADNet) for image denoising. We use image pyramid inputs to restore noise-free results from low-resolution images. In order to realize the interaction of high-frequency and low-frequency information, we design an adaptive spatial-frequency learning unit (ASFU), where a learnable mask is used to separate the information into high-frequency and low-frequency components. In the skip connections, we design a global feature fusion block to enhance the features at different scales. Extensive experiments on both synthetic and real noisy image datasets verify the effectiveness of MADNet compared with current state-of-the-art denoising approaches. |
| title | Learning Multi-scale Spatial-frequency Features for Image Denoising |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Image and Video Processing |
| url | https://arxiv.org/abs/2506.16307 |