{"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/id-blau-image-deblurring-by-implicit","title":"ID-Blau: Image Deblurring by Implicit Diffusion-based reBLurring AUgmentation","arxiv_id":"2312.10998","date":"2023-12-18","proceeding":"CVPR 2024 1","authors":["Jia-Hao Wu","Fu-Jen Tsai","Yan-Tsung Peng","Chung-Chi Tsai","Chia-Wen Lin","Yen-Yu Lin"],"abstract":"Image deblurring aims to remove undesired blurs from an image captured in a dynamic scene. Much research has been dedicated to improving deblurring performance through model architectural designs. However, there is little work on data augmentation for image deblurring. Since continuous motion causes blurred artifacts during image exposure, we aspire to develop a groundbreaking blur augmentation method to generate diverse blurred images by simulating motion trajectories in a continuous space. This paper proposes Implicit Diffusion-based reBLurring AUgmentation (ID-Blau), utilizing a sharp image paired with a controllable blur condition map to produce a corresponding blurred image. We parameterize the blur patterns of a blurred image with their orientations and magnitudes as a pixel-wise blur condition map to simulate motion trajectories and implicitly represent them in a continuous space. By sampling diverse blur conditions, ID-Blau can generate various blurred images unseen in the training set. Experimental results demonstrate that ID-Blau can produce realistic blurred images for training and thus significantly improve performance for state-of-the-art deblurring models. The source code is available at https://github.com/plusgood-steven/ID-Blau.","url_abs":"https://arxiv.org/abs/2312.10998v2","url_pdf":"https://arxiv.org/pdf/2312.10998v2.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":"id-blau-image-deblurring-by-implicit","repo_url":"https://github.com/plusgood-steven/id-blau","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"data-augmentation","task_name":"Data Augmentation"},{"task_slug":"deblurring","task_name":"Deblurring"},{"task_slug":"image-deblurring","task_name":"Image Deblurring"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/deblurring-on-gopro","task":"Deblurring","dataset":"GoPro","model":"ID-Blau (FFTformer)","rank_in_archive_order":9,"of":56,"metrics":{"PSNR":"34.36","SSIM":"0.970"},"uses_additional_data":false},{"leaderboard":"/sota/deblurring-on-gopro","task":"Deblurring","dataset":"GoPro","model":"ID-Blau (Stripformer)","rank_in_archive_order":15,"of":56,"metrics":{"PSNR":"33.66","SSIM":"0.966"},"uses_additional_data":false},{"leaderboard":"/sota/deblurring-on-gopro","task":"Deblurring","dataset":"GoPro","model":"ID-Blau (Restormer)","rank_in_archive_order":19,"of":56,"metrics":{"PSNR":"33.51","SSIM":"0.965"},"uses_additional_data":false},{"leaderboard":"/sota/deblurring-on-hide-trained-on-gopro","task":"Deblurring","dataset":"HIDE (trained on GOPRO)","model":"ID-Blau (FFTformer)","rank_in_archive_order":3,"of":26,"metrics":{"PSNR (sRGB)":"31.94","SSIM (sRGB)":"0.949"},"uses_additional_data":false},{"leaderboard":"/sota/deblurring-on-hide-trained-on-gopro","task":"Deblurring","dataset":"HIDE (trained on GOPRO)","model":"ID-Blau (Restormer)","rank_in_archive_order":7,"of":26,"metrics":{"PSNR (sRGB)":"31.66","SSIM (sRGB)":"0.947"},"uses_additional_data":false},{"leaderboard":"/sota/deblurring-on-hide-trained-on-gopro","task":"Deblurring","dataset":"HIDE (trained on GOPRO)","model":"ID-Blau (Stripformer)","rank_in_archive_order":11,"of":26,"metrics":{"PSNR (sRGB)":"31.50","SSIM (sRGB)":"0.944"},"uses_additional_data":false},{"leaderboard":"/sota/deblurring-on-realblur-j-1","task":"Deblurring","dataset":"RealBlur-J","model":"ID-Blau (Stripformer)","rank_in_archive_order":3,"of":17,"metrics":{"PSNR (sRGB)":"33.77","Params(M)":"20","SSIM (sRGB)":"0.940"},"uses_additional_data":false},{"leaderboard":"/sota/deblurring-on-realblur-j-1","task":"Deblurring","dataset":"RealBlur-J","model":"ID-Blau (Restormer)","rank_in_archive_order":4,"of":17,"metrics":{"PSNR (sRGB)":"33.11","SSIM (sRGB)":"0.937"},"uses_additional_data":false},{"leaderboard":"/sota/deblurring-on-realblur-j-1","task":"Deblurring","dataset":"RealBlur-J","model":"ID-Blau (FFTformer)","rank_in_archive_order":7,"of":17,"metrics":{"PSNR (sRGB)":"32.88","SSIM (sRGB)":"0.934"},"uses_additional_data":false},{"leaderboard":"/sota/deblurring-on-realblur-r","task":"Deblurring","dataset":"RealBlur-R","model":"ID-Blau (Stripformer)","rank_in_archive_order":3,"of":17,"metrics":{"PSNR (sRGB)":"41.06","SSIM (sRGB)":"0.977"},"uses_additional_data":false},{"leaderboard":"/sota/deblurring-on-realblur-r","task":"Deblurring","dataset":"RealBlur-R","model":"ID-Blau (FFTformer)","rank_in_archive_order":5,"of":17,"metrics":{"PSNR (sRGB)":"40.45","SSIM (sRGB)":"0.975"},"uses_additional_data":false},{"leaderboard":"/sota/deblurring-on-realblur-r","task":"Deblurring","dataset":"RealBlur-R","model":"ID-Blau (Restormer)","rank_in_archive_order":6,"of":17,"metrics":{"PSNR (sRGB)":"40.31","SSIM (sRGB)":"0.974"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2312.10998","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.10998"}},"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/plusgood-steven/id-blau","reach":{"status":"ok"}}],"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":1,"samples":[{"code_sha256_prefix":"a473116513ac91bc","entry":"generate_linear_schedule","repo":"plusgood-steven/id-blau","repo_kind":"official","path":"diffusion_inference.py","file_url":"https://github.com/plusgood-steven/id-blau/blob/HEAD/diffusion_inference.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a473116513ac91bc"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}