{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/pixel-level-kernel-estimation-for-blind-super","title":"Pixel-Level Kernel Estimation for Blind Super-Resolution","arxiv_id":null,"date":"2021-11-15","proceeding":"IEEE Access 2021 11","authors":["Jaihyun Lew","Euiyeon Kim","Jae-Pil Heo"],"abstract":"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.","url_abs":"https://ieeexplore.ieee.org/document/9615068","url_pdf":"https://ieeexplore.ieee.org/document/9615068","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"pixel-level-kernel-estimation-for-blind-super","repo_url":"https://github.com/JHLew/PerPix","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"blind-super-resolution","task_name":"Blind Super-Resolution"},{"task_slug":"super-resolution","task_name":"Super-Resolution"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/blind-super-resolution-on-div2krk-4x","task":"Blind Super-Resolution","dataset":"DIV2KRK - 4x upscaling","model":"PerPix","rank_in_archive_order":5,"of":6,"metrics":{"PSNR":"27.69","SSIM":"0.7820"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}