{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/learning-deep-cnn-denoiser-prior-for-image","title":"Learning Deep CNN Denoiser Prior for Image Restoration","arxiv_id":"1704.03264","date":"2017-04-11","proceeding":"CVPR 2017 7","authors":["Kai Zhang","WangMeng Zuo","Shuhang Gu","Lei Zhang"],"abstract":"Model-based optimization methods and discriminative learning methods have\nbeen the two dominant strategies for solving various inverse problems in\nlow-level vision. Typically, those two kinds of methods have their respective\nmerits and drawbacks, e.g., model-based optimization methods are flexible for\nhandling different inverse problems but are usually time-consuming with\nsophisticated priors for the purpose of good performance; in the meanwhile,\ndiscriminative learning methods have fast testing speed but their application\nrange is greatly restricted by the specialized task. Recent works have revealed\nthat, with the aid of variable splitting techniques, denoiser prior can be\nplugged in as a modular part of model-based optimization methods to solve other\ninverse problems (e.g., deblurring). Such an integration induces considerable\nadvantage when the denoiser is obtained via discriminative learning. However,\nthe study of integration with fast discriminative denoiser prior is still\nlacking. To this end, this paper aims to train a set of fast and effective CNN\n(convolutional neural network) denoisers and integrate them into model-based\noptimization method to solve other inverse problems. Experimental results\ndemonstrate that the learned set of denoisers not only achieve promising\nGaussian denoising results but also can be used as prior to deliver good\nperformance for various low-level vision applications.","url_abs":"http://arxiv.org/abs/1704.03264v1","url_pdf":"http://arxiv.org/pdf/1704.03264v1.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":"learning-deep-cnn-denoiser-prior-for-image","repo_url":"https://github.com/cszn/ircnn","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"learning-deep-cnn-denoiser-prior-for-image","repo_url":"https://github.com/theotziol/Depth-images-Denoising","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"color-image-denoising","task_name":"Color Image Denoising"},{"task_slug":"deblurring","task_name":"Deblurring"},{"task_slug":"denoising","task_name":"Denoising"},{"task_slug":"image-denoising","task_name":"Image Denoising"},{"task_slug":"image-restoration","task_name":"Image Restoration"}],"methods":[{"method_slug":"speed","method_name":"SPEED"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/color-image-denoising-on-bsd68-sigma15","task":"Color Image Denoising","dataset":"BSD68 sigma15","model":"Deep CNN Denoiser","rank_in_archive_order":2,"of":4,"metrics":{"PSNR":"33.86"},"uses_additional_data":false},{"leaderboard":"/sota/color-image-denoising-on-bsd68-sigma25","task":"Color Image Denoising","dataset":"BSD68 sigma25","model":"Deep CNN Denoiser","rank_in_archive_order":3,"of":4,"metrics":{"PSNR":"31.16"},"uses_additional_data":false},{"leaderboard":"/sota/color-image-denoising-on-bsd68-sigma35","task":"Color Image Denoising","dataset":"BSD68 sigma35","model":"Deep CNN Denoiser","rank_in_archive_order":1,"of":1,"metrics":{"PSNR":"29.5"},"uses_additional_data":false},{"leaderboard":"/sota/color-image-denoising-on-bsd68-sigma5","task":"Color Image Denoising","dataset":"BSD68 sigma5","model":"Deep CNN Denoiser","rank_in_archive_order":1,"of":1,"metrics":{"PSNR":"40.36"},"uses_additional_data":false},{"leaderboard":"/sota/color-image-denoising-on-cbsd68-sigma50","task":"Color Image Denoising","dataset":"CBSD68 sigma50","model":"IRCNN","rank_in_archive_order":14,"of":18,"metrics":{"PSNR":"27.86"},"uses_additional_data":false},{"leaderboard":"/sota/grayscale-image-denoising-on-bsd68-sigma15","task":"Grayscale Image Denoising","dataset":"BSD68 sigma15","model":"Deep CNN Denoiser","rank_in_archive_order":12,"of":16,"metrics":{"PSNR":"31.63"},"uses_additional_data":false},{"leaderboard":"/sota/grayscale-image-denoising-on-bsd68-sigma25","task":"Grayscale Image Denoising","dataset":"BSD68 sigma25","model":"Deep CNN Denoiser","rank_in_archive_order":13,"of":16,"metrics":{"PSNR":"29.15"},"uses_additional_data":false},{"leaderboard":"/sota/grayscale-image-denoising-on-bsd68-sigma50","task":"Grayscale Image Denoising","dataset":"BSD68 sigma50","model":"Deep CNN Denoiser","rank_in_archive_order":14,"of":15,"metrics":{"PSNR":"26.19"},"uses_additional_data":false},{"leaderboard":"/sota/image-super-resolution-on-set14-2x-upscaling","task":"Image Super-Resolution","dataset":"Set14 - 2x upscaling","model":"Deep CNN Denoiser","rank_in_archive_order":35,"of":35,"metrics":{"PSNR":"30.79"},"uses_additional_data":false},{"leaderboard":"/sota/image-super-resolution-on-set14-3x-upscaling","task":"Image Super-Resolution","dataset":"Set14 - 3x upscaling","model":"Deep CNN Denoiser","rank_in_archive_order":24,"of":24,"metrics":{"PSNR":"27.72"},"uses_additional_data":false},{"leaderboard":"/sota/image-super-resolution-on-set14-4x-upscaling","task":"Image Super-Resolution","dataset":"Set14 - 4x upscaling","model":"Deep CNN Denoiser","rank_in_archive_order":91,"of":104,"metrics":{"PSNR":"27.59"},"uses_additional_data":false},{"leaderboard":"/sota/image-super-resolution-on-set5-2x-upscaling","task":"Image Super-Resolution","dataset":"Set5 - 2x upscaling","model":"Deep CNN Denoiser","rank_in_archive_order":41,"of":41,"metrics":{"PSNR":"35.05"},"uses_additional_data":false},{"leaderboard":"/sota/image-super-resolution-on-set5-3x-upscaling","task":"Image Super-Resolution","dataset":"Set5 - 3x upscaling","model":"Deep CNN Denoiser","rank_in_archive_order":31,"of":32,"metrics":{"PSNR":"31.26"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1704.03264","atlas_url":"https://app.syntology.ai/?focus=1704.03264","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"1704.03264"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1704.03264\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1704.03264"},"call":"get_concepts_for_paper(arxiv_id=\"1704.03264\")"}],"by_repo":[{"repo":"cszn/ircnn","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"theotziol/Depth-images-Denoising","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"0d03fb5ab5b40afb2e93e24886a338a04ce9fd3f67ad78215c341f030d66e5e0","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}