{"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/mm-bsn-self-supervised-image-denoising-for","title":"MM-BSN: Self-Supervised Image Denoising for Real-World with Multi-Mask based on Blind-Spot Network","arxiv_id":"2304.01598","date":"2023-04-04","proceeding":null,"authors":["Dan Zhang","Fangfang Zhou","Yuwen Jiang","Zhengming Fu"],"abstract":"Recent advances in deep learning have been pushing image denoising techniques to a new level. In self-supervised image denoising, blind-spot network (BSN) is one of the most common methods. However, most of the existing BSN algorithms use a dot-based central mask, which is recognized as inefficient for images with large-scale spatially correlated noise. In this paper, we give the definition of large-noise and propose a multi-mask strategy using multiple convolutional kernels masked in different shapes to further break the noise spatial correlation. Furthermore, we propose a novel self-supervised image denoising method that combines the multi-mask strategy with BSN (MM-BSN). We show that different masks can cause significant performance differences, and the proposed MM-BSN can efficiently fuse the features extracted by multi-masked layers, while recovering the texture structures destroyed by multi-masking and information transmission. Our MM-BSN can be used to address the problem of large-noise denoising, which cannot be efficiently handled by other BSN methods. Extensive experiments on public real-world datasets demonstrate that the proposed MM-BSN achieves state-of-the-art performance among self-supervised and even unpaired image denoising methods for sRGB images denoising, without any labelling effort or prior knowledge. Code can be found in https://github.com/dannie125/MM-BSN.","url_abs":"https://arxiv.org/abs/2304.01598v3","url_pdf":"https://arxiv.org/pdf/2304.01598v3.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":"mm-bsn-self-supervised-image-denoising-for","repo_url":"https://github.com/dannie125/mm-bsn","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"mm-bsn-self-supervised-image-denoising-for","repo_url":"https://github.com/secml-lab-vt/EvolvingThreat-DeepfakeImageDetect","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"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2304.01598","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.01598"}},"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/dannie125/mm-bsn","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/secml-lab-vt/EvolvingThreat-DeepfakeImageDetect","reach":{"status":"ok"}}],"summary":{"unverified":3},"by_repo_kind":{"official":{"samples":3,"ran":0,"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":"f2f41ffe55dce700","entry":"get_patch","repo":"dannie125/mm-bsn","repo_kind":"official","path":"DataDeal/DatasetBase.py","file_url":"https://github.com/dannie125/mm-bsn/blob/HEAD/DataDeal/DatasetBase.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f2f41ffe55dce700"}},{"code_sha256_prefix":"1ca14dc53dd7f22e","entry":"is_image_tensor","repo":"dannie125/mm-bsn","repo_kind":"official","path":"DataDeal/DatasetBase.py","file_url":"https://github.com/dannie125/mm-bsn/blob/HEAD/DataDeal/DatasetBase.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1ca14dc53dd7f22e"}},{"code_sha256_prefix":"4057299f4c36663b","entry":"set_dataloader","repo":"dannie125/mm-bsn","repo_kind":"official","path":"DataDeal/DatasetBase.py","file_url":"https://github.com/dannie125/mm-bsn/blob/HEAD/DataDeal/DatasetBase.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4057299f4c36663b"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}