{"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/efficient-multi-scale-network-with-learnable","title":"Efficient Multi-scale Network with Learnable Discrete Wavelet Transform for Blind Motion Deblurring","arxiv_id":"2401.00027","date":"2023-12-29","proceeding":"CVPR 2024 1","authors":["Xin Gao","Tianheng Qiu","Xinyu Zhang","Hanlin Bai","Kang Liu","Xuan Huang","Hu Wei","Guoying Zhang","Huaping Liu"],"abstract":"Coarse-to-fine schemes are widely used in traditional single-image motion deblur; however, in the context of deep learning, existing multi-scale algorithms not only require the use of complex modules for feature fusion of low-scale RGB images and deep semantics, but also manually generate low-resolution pairs of images that do not have sufficient confidence. In this work, we propose a multi-scale network based on single-input and multiple-outputs(SIMO) for motion deblurring. This simplifies the complexity of algorithms based on a coarse-to-fine scheme. To alleviate restoration defects impacting detail information brought about by using a multi-scale architecture, we combine the characteristics of real-world blurring trajectories with a learnable wavelet transform module to focus on the directional continuity and frequency features of the step-by-step transitions between blurred images to sharp images. In conclusion, we propose a multi-scale network with a learnable discrete wavelet transform (MLWNet), which exhibits state-of-the-art performance on multiple real-world deblurred datasets, in terms of both subjective and objective quality as well as computational efficiency.","url_abs":"https://arxiv.org/abs/2401.00027v2","url_pdf":"https://arxiv.org/pdf/2401.00027v2.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":"efficient-multi-scale-network-with-learnable","repo_url":"https://github.com/thqiu0419/mlwnet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"computational-efficiency","task_name":"Computational Efficiency"},{"task_slug":"deblurring","task_name":"Deblurring"}],"methods":[{"method_slug":"focus","method_name":"Focus"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/deblurring-on-gopro","task":"Deblurring","dataset":"GoPro","model":"MLWNet","rank_in_archive_order":12,"of":56,"metrics":{"PSNR":"33.83","SSIM":"0.968"},"uses_additional_data":false},{"leaderboard":"/sota/deblurring-on-rsblur","task":"Deblurring","dataset":"RSBlur","model":"MLWNet","rank_in_archive_order":1,"of":12,"metrics":{"Average PSNR":"34.94","SSIM":"0.880"},"uses_additional_data":false},{"leaderboard":"/sota/deblurring-on-realblur-j-1","task":"Deblurring","dataset":"RealBlur-J","model":"MLWNet","rank_in_archive_order":2,"of":17,"metrics":{"PSNR (sRGB)":"33.84","SSIM (sRGB)":"0.941"},"uses_additional_data":false},{"leaderboard":"/sota/deblurring-on-realblur-r","task":"Deblurring","dataset":"RealBlur-R","model":"MLWNet","rank_in_archive_order":4,"of":17,"metrics":{"PSNR (sRGB)":"40.69","SSIM (sRGB)":"0.976"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2401.00027","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.00027"}},"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/thqiu0419/mlwnet","reach":{"status":"ok","spdx":"NOASSERTION"}}],"summary":{"ran":9,"unverified":3},"by_repo_kind":{"official":{"samples":12,"ran":9,"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":12,"samples":[{"code_sha256_prefix":"1d7ce6d6dd7ff5c1","entry":"calculate_fid","repo":"thqiu0419/mlwnet","repo_kind":"official","path":"basicsr/metrics/fid.py","file_url":"https://github.com/thqiu0419/mlwnet/blob/HEAD/basicsr/metrics/fid.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"1d7ce6d6dd7ff5c1"}},{"code_sha256_prefix":"5170ff1c4106b27a","entry":"compute_feature","repo":"thqiu0419/mlwnet","repo_kind":"official","path":"basicsr/metrics/niqe.py","file_url":"https://github.com/thqiu0419/mlwnet/blob/HEAD/basicsr/metrics/niqe.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"5170ff1c4106b27a"}},{"code_sha256_prefix":"91fa50e293bf2fde","entry":"compute_psnr","repo":"thqiu0419/mlwnet","repo_kind":"official","path":"evaluate_realblur.py","file_url":"https://github.com/thqiu0419/mlwnet/blob/HEAD/evaluate_realblur.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"91fa50e293bf2fde"}},{"code_sha256_prefix":"a1282a48b0941f5d","entry":"estimate_aggd_param","repo":"thqiu0419/mlwnet","repo_kind":"official","path":"basicsr/metrics/niqe.py","file_url":"https://github.com/thqiu0419/mlwnet/blob/HEAD/basicsr/metrics/niqe.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a1282a48b0941f5d"}},{"code_sha256_prefix":"c9fb213c957dc82d","entry":"extract_inception_features","repo":"thqiu0419/mlwnet","repo_kind":"official","path":"basicsr/metrics/fid.py","file_url":"https://github.com/thqiu0419/mlwnet/blob/HEAD/basicsr/metrics/fid.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c9fb213c957dc82d"}},{"code_sha256_prefix":"cd569444547de84f","entry":"get_position_from_periods","repo":"thqiu0419/mlwnet","repo_kind":"official","path":"basicsr/models/lr_scheduler.py","file_url":"https://github.com/thqiu0419/mlwnet/blob/HEAD/basicsr/models/lr_scheduler.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"cd569444547de84f"}},{"code_sha256_prefix":"5167db5f04bebabf","entry":"imread","repo":"thqiu0419/mlwnet","repo_kind":"official","path":"predict.py","file_url":"https://github.com/thqiu0419/mlwnet/blob/HEAD/predict.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"5167db5f04bebabf"}},{"code_sha256_prefix":"95067518dc16b3e5","entry":"reorder_image","repo":"thqiu0419/mlwnet","repo_kind":"official","path":"basicsr/metrics/metric_util.py","file_url":"https://github.com/thqiu0419/mlwnet/blob/HEAD/basicsr/metrics/metric_util.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"95067518dc16b3e5"}},{"code_sha256_prefix":"389a0febc9bbc815","entry":"tensor2img","repo":"thqiu0419/mlwnet","repo_kind":"official","path":"basicsr/metrics/psnr_ssim.py","file_url":"https://github.com/thqiu0419/mlwnet/blob/HEAD/basicsr/metrics/psnr_ssim.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"389a0febc9bbc815"}},{"code_sha256_prefix":"464c3d3b7a1eb4b3","entry":"compute_ssim","repo":"thqiu0419/mlwnet","repo_kind":"official","path":"evaluate_realblur.py","file_url":"https://github.com/thqiu0419/mlwnet/blob/HEAD/evaluate_realblur.py","link_basis":"harvester_set","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":"464c3d3b7a1eb4b3"}},{"code_sha256_prefix":"5aad1c1e328fd4ec","entry":"image_align","repo":"thqiu0419/mlwnet","repo_kind":"official","path":"evaluate_realblur.py","file_url":"https://github.com/thqiu0419/mlwnet/blob/HEAD/evaluate_realblur.py","link_basis":"harvester_set","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":"5aad1c1e328fd4ec"}},{"code_sha256_prefix":"0029cb1566e47350","entry":"niqe","repo":"thqiu0419/mlwnet","repo_kind":"official","path":"basicsr/metrics/niqe.py","file_url":"https://github.com/thqiu0419/mlwnet/blob/HEAD/basicsr/metrics/niqe.py","link_basis":"harvester_set","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":"0029cb1566e47350"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}