Error feedback denoising network
Abstract Recently, deep convolutional neural networks have been successfully used for image denoising due to their favourable performance. This paper examines the error feedback mechanism to image denoising and propose an error feedback denoising network. Specifically, we use the down‐and‐up project...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2021-05-01
|
| Series: | IET Image Processing |
| Subjects: | |
| Online Access: | https://doi.org/10.1049/ipr2.12121 |
| _version_ | 1828237051697299456 |
|---|---|
| author | Ruizhi Hou Fang Li |
| author_facet | Ruizhi Hou Fang Li |
| author_sort | Ruizhi Hou |
| collection | DOAJ |
| description | Abstract Recently, deep convolutional neural networks have been successfully used for image denoising due to their favourable performance. This paper examines the error feedback mechanism to image denoising and propose an error feedback denoising network. Specifically, we use the down‐and‐up projection sequence to estimate the noise feature. By the residual connection, the clean structures are removed from the noise features. The essential difference between the proposed network and other existing feedback networks is the projection sequence. Our error feedback projection sequence is down‐and‐up, which is more suitable for image denoising than the existing up‐and‐down order. Moreover, we design a compression block to improve the expression ability of the general 1×1 convolutional compression layer. The advantage of our well‐designed down‐and‐up block is that the network parameters are fewer than other feedback networks and the receptive field is enlarged. We have implemented our error feedback denoising network on denoising and JPEG image deblocking. Extensive experiments verify the effectiveness of our down‐and‐up block and demonstrate that our error feedback denoising network is comparable with the state‐of‐the‐art. The code will be open source. The source codes for reproducing the results can be found at: https://github.com/Houruizhi/EFDN. |
| first_indexed | 2024-04-12T20:43:21Z |
| format | Article |
| id | doaj.art-0c4b4fd99a5348d58b8323a95aff1b61 |
| institution | Directory Open Access Journal |
| issn | 1751-9659 1751-9667 |
| language | English |
| last_indexed | 2024-04-12T20:43:21Z |
| publishDate | 2021-05-01 |
| publisher | Wiley |
| record_format | Article |
| series | IET Image Processing |
| spelling | doaj.art-0c4b4fd99a5348d58b8323a95aff1b612022-12-22T03:17:21ZengWileyIET Image Processing1751-96591751-96672021-05-011571508151710.1049/ipr2.12121Error feedback denoising networkRuizhi Hou0Fang Li1School of Mathematical Sciences East China Normal University Shanghai ChinaSchool of Mathematical Sciences and Shanghai Key Laboratory of PMMP East China Normal University Shanghai ChinaAbstract Recently, deep convolutional neural networks have been successfully used for image denoising due to their favourable performance. This paper examines the error feedback mechanism to image denoising and propose an error feedback denoising network. Specifically, we use the down‐and‐up projection sequence to estimate the noise feature. By the residual connection, the clean structures are removed from the noise features. The essential difference between the proposed network and other existing feedback networks is the projection sequence. Our error feedback projection sequence is down‐and‐up, which is more suitable for image denoising than the existing up‐and‐down order. Moreover, we design a compression block to improve the expression ability of the general 1×1 convolutional compression layer. The advantage of our well‐designed down‐and‐up block is that the network parameters are fewer than other feedback networks and the receptive field is enlarged. We have implemented our error feedback denoising network on denoising and JPEG image deblocking. Extensive experiments verify the effectiveness of our down‐and‐up block and demonstrate that our error feedback denoising network is comparable with the state‐of‐the‐art. The code will be open source. The source codes for reproducing the results can be found at: https://github.com/Houruizhi/EFDN.https://doi.org/10.1049/ipr2.12121deep convolutional neural networkserror feedback strategyimage denoisingImage and video codingComputer vision and image processing techniquesNeural nets |
| spellingShingle | Ruizhi Hou Fang Li Error feedback denoising network IET Image Processing deep convolutional neural networks error feedback strategy image denoising Image and video coding Computer vision and image processing techniques Neural nets |
| title | Error feedback denoising network |
| title_full | Error feedback denoising network |
| title_fullStr | Error feedback denoising network |
| title_full_unstemmed | Error feedback denoising network |
| title_short | Error feedback denoising network |
| title_sort | error feedback denoising network |
| topic | deep convolutional neural networks error feedback strategy image denoising Image and video coding Computer vision and image processing techniques Neural nets |
| url | https://doi.org/10.1049/ipr2.12121 |
| work_keys_str_mv | AT ruizhihou errorfeedbackdenoisingnetwork AT fangli errorfeedbackdenoisingnetwork |