{"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/realistic-blur-synthesis-for-learning-image","title":"Realistic Blur Synthesis for Learning Image Deblurring","arxiv_id":"2202.08771","date":"2022-02-17","proceeding":null,"authors":["Jaesung Rim","Geonung Kim","Jungeon Kim","Junyong Lee","Seungyong Lee","Sunghyun Cho"],"abstract":"Training learning-based deblurring methods demands a tremendous amount of blurred and sharp image pairs. Unfortunately, existing synthetic datasets are not realistic enough, and deblurring models trained on them cannot handle real blurred images effectively. While real datasets have recently been proposed, they provide limited diversity of scenes and camera settings, and capturing real datasets for diverse settings is still challenging. To resolve this, this paper analyzes various factors that introduce differences between real and synthetic blurred images. To this end, we present RSBlur, a novel dataset with real blurred images and the corresponding sharp image sequences to enable a detailed analysis of the difference between real and synthetic blur. With the dataset, we reveal the effects of different factors in the blur generation process. Based on the analysis, we also present a novel blur synthesis pipeline to synthesize more realistic blur. We show that our synthesis pipeline can improve the deblurring performance on real blurred images.","url_abs":"https://arxiv.org/abs/2202.08771v3","url_pdf":"https://arxiv.org/pdf/2202.08771v3.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":"realistic-blur-synthesis-for-learning-image","repo_url":"https://github.com/rimchang/Rsblur","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"deblurring","task_name":"Deblurring"},{"task_slug":"diversity","task_name":"Diversity"},{"task_slug":"image-deblurring","task_name":"Image Deblurring"}],"methods":[],"datasets_introduced":[{"slug":"rsblur","name":"RSBlur","full_name":""}],"methods_introduced":[],"results":[{"leaderboard":"/sota/deblurring-on-rsblur-trained-on-synthetic","task":"Deblurring","dataset":"RSBlur (trained on synthetic)","model":"MIMO-UNet + Realistic blur","rank_in_archive_order":1,"of":2,"metrics":{"Average PSNR":"32.08"},"uses_additional_data":false},{"leaderboard":"/sota/deblurring-on-rsblur-trained-on-synthetic","task":"Deblurring","dataset":"RSBlur (trained on synthetic)","model":"SRN-Deblur + Realistic blur","rank_in_archive_order":2,"of":2,"metrics":{"Average PSNR":"32.06"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2202.08771","atlas_url":"https://app.syntology.ai/?focus=2202.08771","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2202.08771"}},"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/rimchang/Rsblur","reach":null}],"summary":{"unverified":1},"by_repo_kind":{"official":{"samples":1,"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":1,"samples":[{"code_sha256_prefix":"2b823fc42e14c395","entry":"RealisticGoProABMEDataset","repo":"rimchang/Rsblur","repo_kind":"official","path":"Uformer-RSBlur/dataset/dataset_RealisticDeblur.py","file_url":"https://github.com/rimchang/Rsblur/blob/HEAD/Uformer-RSBlur/dataset/dataset_RealisticDeblur.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"2b823fc42e14c395"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}