{"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/cycleisp-real-image-restoration-via-improved","title":"CycleISP: Real Image Restoration via Improved Data Synthesis","arxiv_id":"2003.07761","date":"2020-03-17","proceeding":"CVPR 2020 6","authors":["Syed Waqas Zamir","Aditya Arora","Salman Khan","Munawar Hayat","Fahad Shahbaz Khan","Ming-Hsuan Yang","Ling Shao"],"abstract":"The availability of large-scale datasets has helped unleash the true potential of deep convolutional neural networks (CNNs). However, for the single-image denoising problem, capturing a real dataset is an unacceptably expensive and cumbersome procedure. Consequently, image denoising algorithms are mostly developed and evaluated on synthetic data that is usually generated with a widespread assumption of additive white Gaussian noise (AWGN). While the CNNs achieve impressive results on these synthetic datasets, they do not perform well when applied on real camera images, as reported in recent benchmark datasets. This is mainly because the AWGN is not adequate for modeling the real camera noise which is signal-dependent and heavily transformed by the camera imaging pipeline. In this paper, we present a framework that models camera imaging pipeline in forward and reverse directions. It allows us to produce any number of realistic image pairs for denoising both in RAW and sRGB spaces. By training a new image denoising network on realistic synthetic data, we achieve the state-of-the-art performance on real camera benchmark datasets. The parameters in our model are ~5 times lesser than the previous best method for RAW denoising. Furthermore, we demonstrate that the proposed framework generalizes beyond image denoising problem e.g., for color matching in stereoscopic cinema. The source code and pre-trained models are available at https://github.com/swz30/CycleISP.","url_abs":"https://arxiv.org/abs/2003.07761v1","url_pdf":"https://arxiv.org/pdf/2003.07761v1.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":"cycleisp-real-image-restoration-via-improved","repo_url":"https://github.com/swz30/CycleISP","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"cycleisp-real-image-restoration-via-improved","repo_url":"https://github.com/GarrickZ2/Image-Denoising","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"cycleisp-real-image-restoration-via-improved","repo_url":"https://github.com/mv-lab/AISP","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"cycleisp-real-image-restoration-via-improved","repo_url":"https://github.com/swz30/MIRNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"cycleisp-real-image-restoration-via-improved","repo_url":"https://github.com/swz30/MPRNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"cycleisp-real-image-restoration-via-improved","repo_url":"https://github.com/swz30/mirnetv2","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"cycleisp-real-image-restoration-via-improved","repo_url":"https://github.com/swz30/restormer","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"cycleisp-real-image-restoration-via-improved","repo_url":"https://github.com/zhangximing213/denoise","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"denoising","task_name":"Denoising"},{"task_slug":"image-denoising","task_name":"Image Denoising"},{"task_slug":"image-restoration","task_name":"Image Restoration"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-denoising-on-dnd","task":"Image Denoising","dataset":"DND","model":"CycleISP","rank_in_archive_order":12,"of":16,"metrics":{"PSNR (sRGB)":"39.56","SSIM (sRGB)":"0.956"},"uses_additional_data":true},{"leaderboard":"/sota/image-denoising-on-sidd","task":"Image Denoising","dataset":"SIDD","model":"CycleISP","rank_in_archive_order":14,"of":22,"metrics":{"PSNR (sRGB)":"39.52","SSIM (sRGB)":"0.957"},"uses_additional_data":true}],"syntology":{"syntology_url":"https://syntology.ai/paper/2003.07761","atlas_url":"https://app.syntology.ai/?focus=2003.07761","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":"2003.07761"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2003.07761\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2003.07761"},"call":"get_concepts_for_paper(arxiv_id=\"2003.07761\")"}],"by_repo":[{"repo":"swz30/CycleISP","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2102.02808"],"harvested_for_calls":[{"arxiv_id":"2102.02808","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2102.02808"},"call":"get_harvested_code_for_paper(arxiv_id=\"2102.02808\")"}]},{"repo":"GarrickZ2/Image-Denoising","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2204.02844"],"harvested_for_calls":[{"arxiv_id":"2204.02844","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2204.02844"},"call":"get_harvested_code_for_paper(arxiv_id=\"2204.02844\")"}]},{"repo":"mv-lab/AISP","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"swz30/MIRNet","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"swz30/MPRNet","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2102.02808"],"harvested_for_calls":[{"arxiv_id":"2102.02808","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2102.02808"},"call":"get_harvested_code_for_paper(arxiv_id=\"2102.02808\")"}]},{"repo":"swz30/mirnetv2","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2102.02808"],"harvested_for_calls":[{"arxiv_id":"2102.02808","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2102.02808"},"call":"get_harvested_code_for_paper(arxiv_id=\"2102.02808\")"}]},{"repo":"swz30/restormer","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":2,"harvested_for":["2102.02808","Zamir_Restormer_Efficient_Transformer_for_High-Resolution_Image_Restoration_CVPR_2022_paper"],"harvested_for_calls":[{"arxiv_id":"2102.02808","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2102.02808"},"call":"get_harvested_code_for_paper(arxiv_id=\"2102.02808\")"}]},{"repo":"zhangximing213/denoise","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","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":"c08df82c269fb0c2f30ba3e444d1f476e1e636cd11527acef71900f346362bf8","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}