{"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/one-size-fits-all-hypernetwork-for-tunable","title":"Hypernetwork-Based Adaptive Image Restoration","arxiv_id":"2206.05970","date":"2022-06-13","proceeding":null,"authors":["Shai Aharon","Gil Ben-Artzi"],"abstract":"Adaptive image restoration models can restore images with different degradation levels at inference time without the need to retrain the model. We present an approach that is highly accurate and allows a significant reduction in the number of parameters. In contrast to existing methods, our approach can restore images using a single fixed-size model, regardless of the number of degradation levels. On popular datasets, our approach yields state-of-the-art results in terms of size and accuracy for a variety of image restoration tasks, including denoising, deJPEG, and super-resolution.","url_abs":"https://arxiv.org/abs/2206.05970v3","url_pdf":"https://arxiv.org/pdf/2206.05970v3.pdf","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":"one-size-fits-all-hypernetwork-for-tunable","repo_url":"https://github.com/ifryed/HyperRes","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"color-image-denoising","task_name":"Color Image Denoising"},{"task_slug":"denoising","task_name":"Denoising"},{"task_slug":"image-denoising","task_name":"Image Denoising"},{"task_slug":"image-restoration","task_name":"Image Restoration"},{"task_slug":"image-super-resolution","task_name":"Image Super-Resolution"},{"task_slug":"jpeg-artifact-correction","task_name":"JPEG Artifact Correction"},{"task_slug":"jpeg-artifact-removal","task_name":"JPEG Artifact Removal"},{"task_slug":"super-resolution","task_name":"Super-Resolution"}],"methods":[{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"hypernetwork","method_name":"HyperNetwork"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-block","method_name":"Residual Block"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"tunable-network","method_name":"Tunable Network"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/color-image-denoising-on-cbsd68-sigma15","task":"Color Image Denoising","dataset":"CBSD68 sigma15","model":"HyperRes","rank_in_archive_order":6,"of":10,"metrics":{"PSNR":"34.02","SSIM":"0.95"},"uses_additional_data":false},{"leaderboard":"/sota/color-image-denoising-on-cbsd68-sigma25","task":"Color Image Denoising","dataset":"CBSD68 sigma25","model":"HyperRes","rank_in_archive_order":5,"of":9,"metrics":{"PSNR":"31.41","SSIM":"0.89"},"uses_additional_data":false},{"leaderboard":"/sota/color-image-denoising-on-cbsd68-sigma35","task":"Color Image Denoising","dataset":"CBSD68 sigma35","model":"HyperRes","rank_in_archive_order":2,"of":6,"metrics":{"PSNR":"29.8","SSIM":"0.85"},"uses_additional_data":false},{"leaderboard":"/sota/color-image-denoising-on-cbsd68-sigma45","task":"Color Image Denoising","dataset":"CBSD68 sigma45","model":"HyperRes","rank_in_archive_order":1,"of":2,"metrics":{"PSNR":"28.64","SSIM":"0.81"},"uses_additional_data":false},{"leaderboard":"/sota/color-image-denoising-on-cbsd68-sigma5","task":"Color Image Denoising","dataset":"CBSD68 sigma5","model":"HyperRes","rank_in_archive_order":2,"of":3,"metrics":{"PSNR":"39.96","SSIM":"0.98"},"uses_additional_data":false},{"leaderboard":"/sota/color-image-denoising-on-cbsd68-sigma55","task":"Color Image Denoising","dataset":"CBSD68 sigma55","model":"HyperRes","rank_in_archive_order":1,"of":2,"metrics":{"PSNR":"27.78","SSIM":"0.78"},"uses_additional_data":false},{"leaderboard":"/sota/color-image-denoising-on-cbsd68-sigma65","task":"Color Image Denoising","dataset":"CBSD68 sigma65","model":"HyperRes","rank_in_archive_order":1,"of":2,"metrics":{"PSNR":"27.06","SSIM":"0.76"},"uses_additional_data":false},{"leaderboard":"/sota/color-image-denoising-on-cbsd68-sigma75","task":"Color Image Denoising","dataset":"CBSD68 sigma75","model":"HyperRes","rank_in_archive_order":1,"of":4,"metrics":{"PSNR":"26.46","SSIM":"0.73"},"uses_additional_data":false},{"leaderboard":"/sota/color-image-denoising-on-cbsd68-sigma85","task":"Color Image Denoising","dataset":"CBSD68 sigma85","model":"HyperRes","rank_in_archive_order":1,"of":1,"metrics":{"PSNR":"25.95","SSIM":"0.71"},"uses_additional_data":false},{"leaderboard":"/sota/image-super-resolution-on-set5-2x-upscaling","task":"Image Super-Resolution","dataset":"Set5 - 2x upscaling","model":"HyperRes","rank_in_archive_order":40,"of":41,"metrics":{"PSNR":"36.69","SSIM":"0.94"},"uses_additional_data":false},{"leaderboard":"/sota/image-super-resolution-on-set5-3x-upscaling","task":"Image Super-Resolution","dataset":"Set5 - 3x upscaling","model":"HyperRes","rank_in_archive_order":32,"of":32,"metrics":{"PSNR":"29.77","SSIM":"0.84"},"uses_additional_data":false},{"leaderboard":"/sota/image-super-resolution-on-set5-5x-upscaling","task":"Image Super-Resolution","dataset":"Set5 - 5x upscaling","model":"HyperRes","rank_in_archive_order":1,"of":1,"metrics":{"PSNR":"25.63","SSIM":"0.74"},"uses_additional_data":false},{"leaderboard":"/sota/image-super-resolution-on-set5-6x-upscaling","task":"Image Super-Resolution","dataset":"Set5 - 6x upscaling","model":"HyperRes","rank_in_archive_order":1,"of":1,"metrics":{"PSNR":"24.92","SSIM":"0.71"},"uses_additional_data":false},{"leaderboard":"/sota/jpeg-artifact-correction-on-live1-quality-30-1","task":"JPEG Artifact Correction","dataset":"LIVE1 (Quality 30 Grayscale)","model":"HyperRes","rank_in_archive_order":7,"of":7,"metrics":{"PSNR":"32.56","SSIM":"0.91"},"uses_additional_data":false},{"leaderboard":"/sota/jpeg-artifact-correction-on-live1-quality-10-1","task":"JPEG Artifact Correction","dataset":"Live1 (Quality 10 Grayscale)","model":"HyperRes","rank_in_archive_order":13,"of":13,"metrics":{"PSNR":"28.81","SSIM":"0.82"},"uses_additional_data":false},{"leaderboard":"/sota/jpeg-artifact-correction-on-live1-quality-50","task":"JPEG Artifact Correction","dataset":"Live1 (Quality 50 Grayscale)","model":"HyperRes","rank_in_archive_order":1,"of":1,"metrics":{"PSNR":"34.39","SSIM":"0.94"},"uses_additional_data":false},{"leaderboard":"/sota/jpeg-artifact-correction-on-live1-quality-70","task":"JPEG Artifact Correction","dataset":"Live1 (Quality 70 Grayscale)","model":"HyperRes","rank_in_archive_order":1,"of":1,"metrics":{"PSNR":"36.38","SSIM":"0.96"},"uses_additional_data":false},{"leaderboard":"/sota/jpeg-artifact-correction-on-live1-quality-80","task":"JPEG Artifact Correction","dataset":"Live1 (Quality 80 Grayscale)","model":"HyperRes","rank_in_archive_order":1,"of":1,"metrics":{"PSNR":"38.09","SSIM":"0.97"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2206.05970","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.05970"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ifryed/HyperRes","reach":null}],"summary":{"ran_fixture":1},"by_repo_kind":{"official":{"samples":1,"ran":1,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":1,"samples":[{"code_sha256_prefix":"10173cb4647ea461","entry":"addNoise","repo":"ifryed/HyperRes","repo_kind":"official","path":"live_demo.py","file_url":"https://github.com/ifryed/HyperRes/blob/HEAD/live_demo.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"10173cb4647ea461"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}