Pixel-Level Kernel Estimation for Blind Super-Resolution
Throughout the past several years, deep learning-based models have achieved success in super-resolution (SR). The majority of these works assume that low-resolution (LR) images are ‘uniformly’ degraded from their corresponding high-resolution (HR) images using predefined blur k...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2021-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9615068/ |
| _version_ | 1818837563428831232 |
|---|---|
| author | Jaihyun Lew Euiyeon Kim Jae-Pil Heo |
| author_facet | Jaihyun Lew Euiyeon Kim Jae-Pil Heo |
| author_sort | Jaihyun Lew |
| collection | DOAJ |
| description | Throughout the past several years, deep learning-based models have achieved success in super-resolution (SR). The majority of these works assume that low-resolution (LR) images are ‘uniformly’ degraded from their corresponding high-resolution (HR) images using predefined blur kernels — all regions of an image undergoing an identical degradation process. Furthermore, based on this assumption, there have been attempts to estimate the blur kernel of a given LR image, since correct kernel priors are known to be helpful in super-resolution. Although it has been known that blur kernels of real images are non-uniform (spatially varying), current kernel estimation algorithms are mostly done at image-level, estimating one kernel per image. These algorithms inevitably become sub-optimal in handling scenarios where an image is degraded non-uniformly. A divide-and-conquer form of approach, dividing an image into several patches for individual kernel estimation and SR can be a simple solution for this matter. Nevertheless, this approach fails in practice. In this paper, we address this issue by pixel-level kernel estimation. The three main components for training a SR framework based on pixel-level kernel estimation are as follows: Kernel Collage — a method for synthesizing non-uniformly degraded LR images, designed considering the coherency of kernels at neighboring regions while abruptly changing at times, the indirect loss — a novel loss for training the kernel estimator, based on the reconstruction loss, and an additional optimization — a scheme to robustify the SR network to minor errors in kernel estimations. Extensive experiments show the superiority of pixel-level kernel estimation in blind SR, surpassing state-of-the-art methods in terms of quantitative and qualitative results. |
| first_indexed | 2024-12-19T03:24:29Z |
| format | Article |
| id | doaj.art-c8c65f021cb94f388335cb8262fbb319 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-19T03:24:29Z |
| publishDate | 2021-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-c8c65f021cb94f388335cb8262fbb3192022-12-21T20:37:41ZengIEEEIEEE Access2169-35362021-01-01915280315281810.1109/ACCESS.2021.31282729615068Pixel-Level Kernel Estimation for Blind Super-ResolutionJaihyun Lew0https://orcid.org/0000-0003-3934-2879Euiyeon Kim1Jae-Pil Heo2https://orcid.org/0000-0001-9684-7641Department of Artificial Intelligence, Sungkyunkwan University, Suwon, South KoreaDepartment of Artificial Intelligence, Sungkyunkwan University, Suwon, South KoreaDepartment of Artificial Intelligence, Sungkyunkwan University, Suwon, South KoreaThroughout the past several years, deep learning-based models have achieved success in super-resolution (SR). The majority of these works assume that low-resolution (LR) images are ‘uniformly’ degraded from their corresponding high-resolution (HR) images using predefined blur kernels — all regions of an image undergoing an identical degradation process. Furthermore, based on this assumption, there have been attempts to estimate the blur kernel of a given LR image, since correct kernel priors are known to be helpful in super-resolution. Although it has been known that blur kernels of real images are non-uniform (spatially varying), current kernel estimation algorithms are mostly done at image-level, estimating one kernel per image. These algorithms inevitably become sub-optimal in handling scenarios where an image is degraded non-uniformly. A divide-and-conquer form of approach, dividing an image into several patches for individual kernel estimation and SR can be a simple solution for this matter. Nevertheless, this approach fails in practice. In this paper, we address this issue by pixel-level kernel estimation. The three main components for training a SR framework based on pixel-level kernel estimation are as follows: Kernel Collage — a method for synthesizing non-uniformly degraded LR images, designed considering the coherency of kernels at neighboring regions while abruptly changing at times, the indirect loss — a novel loss for training the kernel estimator, based on the reconstruction loss, and an additional optimization — a scheme to robustify the SR network to minor errors in kernel estimations. Extensive experiments show the superiority of pixel-level kernel estimation in blind SR, surpassing state-of-the-art methods in terms of quantitative and qualitative results.https://ieeexplore.ieee.org/document/9615068/Blind super-resolutionblur kernel estimationpixel-level estimationspatially varying degradation |
| spellingShingle | Jaihyun Lew Euiyeon Kim Jae-Pil Heo Pixel-Level Kernel Estimation for Blind Super-Resolution IEEE Access Blind super-resolution blur kernel estimation pixel-level estimation spatially varying degradation |
| title | Pixel-Level Kernel Estimation for Blind Super-Resolution |
| title_full | Pixel-Level Kernel Estimation for Blind Super-Resolution |
| title_fullStr | Pixel-Level Kernel Estimation for Blind Super-Resolution |
| title_full_unstemmed | Pixel-Level Kernel Estimation for Blind Super-Resolution |
| title_short | Pixel-Level Kernel Estimation for Blind Super-Resolution |
| title_sort | pixel level kernel estimation for blind super resolution |
| topic | Blind super-resolution blur kernel estimation pixel-level estimation spatially varying degradation |
| url | https://ieeexplore.ieee.org/document/9615068/ |
| work_keys_str_mv | AT jaihyunlew pixellevelkernelestimationforblindsuperresolution AT euiyeonkim pixellevelkernelestimationforblindsuperresolution AT jaepilheo pixellevelkernelestimationforblindsuperresolution |