{"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/learnability-enhancement-for-low-light-raw","title":"Learnability Enhancement for Low-light Raw Denoising: Where Paired Real Data Meets Noise Modeling","arxiv_id":"2207.06103","date":"2022-07-13","proceeding":null,"authors":["Hansen Feng","Lizhi Wang","Yuzhi Wang","Hua Huang"],"abstract":"Low-light raw denoising is an important and valuable task in computational photography where learning-based methods trained with paired real data are mainstream. However, the limited data volume and complicated noise distribution have constituted a learnability bottleneck for paired real data, which limits the denoising performance of learning-based methods. To address this issue, we present a learnability enhancement strategy to reform paired real data according to noise modeling. Our strategy consists of two efficient techniques: shot noise augmentation (SNA) and dark shading correction (DSC). Through noise model decoupling, SNA improves the precision of data mapping by increasing the data volume and DSC reduces the complexity of data mapping by reducing the noise complexity. Extensive results on the public datasets and real imaging scenarios collectively demonstrate the state-of-the-art performance of our method. Our code is available at: https://github.com/megvii-research/PMN.","url_abs":"https://arxiv.org/abs/2207.06103v2","url_pdf":"https://arxiv.org/pdf/2207.06103v2.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":"learnability-enhancement-for-low-light-raw","repo_url":"https://github.com/megvii-research/pmn","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"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":"PMN","rank_in_archive_order":2,"of":9,"metrics":{"PSNR (Raw)":"46.50","SSIM (Raw)":"0.985"},"uses_additional_data":false},{"leaderboard":"/sota/image-denoising-on-eld-sonya7s2-x200","task":"Image Denoising","dataset":"ELD SonyA7S2 x200","model":"PMN","rank_in_archive_order":2,"of":10,"metrics":{"PSNR (Raw)":"44.51","SSIM (Raw)":"0.973"},"uses_additional_data":false},{"leaderboard":"/sota/image-denoising-on-sid-sonya7s2-x100","task":"Image Denoising","dataset":"SID SonyA7S2 x100","model":"PMN","rank_in_archive_order":1,"of":5,"metrics":{"PSNR (Raw)":"43.16","SSIM (Raw)":"0.960"},"uses_additional_data":false},{"leaderboard":"/sota/image-denoising-on-sid-sonya7s2-x250","task":"Image Denoising","dataset":"SID SonyA7S2 x250","model":"PMN","rank_in_archive_order":2,"of":10,"metrics":{"PSNR (Raw)":"40.92","SSIM (Raw)":"0.947"},"uses_additional_data":false},{"leaderboard":"/sota/image-denoising-on-sid-x100","task":"Image Denoising","dataset":"SID x100","model":"PMN","rank_in_archive_order":2,"of":8,"metrics":{"PSNR (Raw)":"43.16","SSIM":"0.960"},"uses_additional_data":false},{"leaderboard":"/sota/image-denoising-on-sid-x300","task":"Image Denoising","dataset":"SID x300","model":"PMN","rank_in_archive_order":2,"of":8,"metrics":{"PSNR (Raw)":"37.77","SSIM":"0.934"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2207.06103","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}