Towards Controllable Real Image Denoising with Camera Parameters
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_ | 1866911136991936512 |
|---|---|
| author | Oh, Youngjin Kwon, Junhyeong Lee, Keuntek Cho, Nam Ik |
| author_facet | Oh, Youngjin Kwon, Junhyeong Lee, Keuntek Cho, Nam Ik |
| contents | Recent deep learning-based image denoising methods have shown impressive performance; however, many lack the flexibility to adjust the denoising strength based on the noise levels, camera settings, and user preferences. In this paper, we introduce a new controllable denoising framework that adaptively removes noise from images by utilizing information from camera parameters. Specifically, we focus on ISO, shutter speed, and F-number, which are closely related to noise levels. We convert these selected parameters into a vector to control and enhance the performance of the denoising network. Experimental results show that our method seamlessly adds controllability to standard denoising neural networks and improves their performance. Code is available at https://github.com/OBAKSA/CPADNet. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_01587 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Towards Controllable Real Image Denoising with Camera Parameters Oh, Youngjin Kwon, Junhyeong Lee, Keuntek Cho, Nam Ik Computer Vision and Pattern Recognition Image and Video Processing Recent deep learning-based image denoising methods have shown impressive performance; however, many lack the flexibility to adjust the denoising strength based on the noise levels, camera settings, and user preferences. In this paper, we introduce a new controllable denoising framework that adaptively removes noise from images by utilizing information from camera parameters. Specifically, we focus on ISO, shutter speed, and F-number, which are closely related to noise levels. We convert these selected parameters into a vector to control and enhance the performance of the denoising network. Experimental results show that our method seamlessly adds controllability to standard denoising neural networks and improves their performance. Code is available at https://github.com/OBAKSA/CPADNet. |
| title | Towards Controllable Real Image Denoising with Camera Parameters |
| topic | Computer Vision and Pattern Recognition Image and Video Processing |
| url | https://arxiv.org/abs/2507.01587 |