{"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/rethinking-noise-synthesis-and-modeling-in-1","title":"Rethinking Noise Synthesis and Modeling in Raw Denoising","arxiv_id":"2110.04756","date":"2021-10-10","proceeding":"ICCV 2021 10","authors":["Yi Zhang","Hongwei Qin","Xiaogang Wang","Hongsheng Li"],"abstract":"The lack of large-scale real raw image denoising dataset gives rise to challenges on synthesizing realistic raw image noise for training denoising models. However, the real raw image noise is contributed by many noise sources and varies greatly among different sensors. Existing methods are unable to model all noise sources accurately, and building a noise model for each sensor is also laborious. In this paper, we introduce a new perspective to synthesize noise by directly sampling from the sensor's real noise. It inherently generates accurate raw image noise for different camera sensors. Two efficient and generic techniques: pattern-aligned patch sampling and high-bit reconstruction help accurate synthesis of spatial-correlated noise and high-bit noise respectively. We conduct systematic experiments on SIDD and ELD datasets. The results show that (1) our method outperforms existing methods and demonstrates wide generalization on different sensors and lighting conditions. (2) Recent conclusions derived from DNN-based noise modeling methods are actually based on inaccurate noise parameters. The DNN-based methods still cannot outperform physics-based statistical methods.","url_abs":"https://arxiv.org/abs/2110.04756v3","url_pdf":"https://arxiv.org/pdf/2110.04756v3.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":"rethinking-noise-synthesis-and-modeling-in-1","repo_url":"https://github.com/zhangyi-3/noise-synthesis","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"denoising","task_name":"Denoising"},{"task_slug":"image-denoising","task_name":"Image Denoising"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-denoising-on-eld-sonya7s2-x100","task":"Image Denoising","dataset":"ELD SonyA7S2 x100","model":"SFRN","rank_in_archive_order":3,"of":9,"metrics":{"PSNR (Raw)":"46.02","SSIM (Raw)":"0.977"},"uses_additional_data":false},{"leaderboard":"/sota/image-denoising-on-eld-sonya7s2-x200","task":"Image Denoising","dataset":"ELD SonyA7S2 x200","model":"SFRN","rank_in_archive_order":3,"of":10,"metrics":{"PSNR (Raw)":"44.10","SSIM (Raw)":"0.964"},"uses_additional_data":false},{"leaderboard":"/sota/image-denoising-on-sid-sonya7s2-x100","task":"Image Denoising","dataset":"SID SonyA7S2 x100","model":"SFRN","rank_in_archive_order":2,"of":5,"metrics":{"PSNR (Raw)":"42.29","SSIM (Raw)":"0.951"},"uses_additional_data":false},{"leaderboard":"/sota/image-denoising-on-sid-sonya7s2-x250","task":"Image Denoising","dataset":"SID SonyA7S2 x250","model":"SFRN","rank_in_archive_order":3,"of":10,"metrics":{"PSNR (Raw)":"40.22","SSIM (Raw)":"0.938"},"uses_additional_data":false},{"leaderboard":"/sota/image-denoising-on-sid-x100","task":"Image Denoising","dataset":"SID x100","model":"SFRN","rank_in_archive_order":3,"of":8,"metrics":{"PSNR (Raw)":"42.29","SSIM":"0.951"},"uses_additional_data":false},{"leaderboard":"/sota/image-denoising-on-sid-x300","task":"Image Denoising","dataset":"SID x300","model":"SFRN","rank_in_archive_order":3,"of":8,"metrics":{"PSNR (Raw)":"36.87","SSIM":"0.917"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2110.04756","atlas_url":"https://app.syntology.ai/?focus=2110.04756","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.04756"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/zhangyi-3/noise-synthesis","reach":null}],"summary":{"ran_honours":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":0,"samples":[{"code_sha256_prefix":"87bc338739bd05f4","entry":"noise_profiles","repo":"zhangyi-3/noise-synthesis","repo_kind":"official","path":"synthesize.py","file_url":"https://github.com/zhangyi-3/noise-synthesis/blob/HEAD/synthesize.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"87bc338739bd05f4"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}