{"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-spatio-temporal-recurrent-neural-1","title":"Real-world Video Deblurring: A Benchmark Dataset and An Efficient Recurrent Neural Network","arxiv_id":"2106.16028","date":"2021-06-30","proceeding":"ECCV 2020 8","authors":["Zhihang Zhong","Ye Gao","Yinqiang Zheng","Bo Zheng","Imari Sato"],"abstract":"Real-world video deblurring in real time still remains a challenging task due to the complexity of spatially and temporally varying blur itself and the requirement of low computational cost. To improve the network efficiency, we adopt residual dense blocks into RNN cells, so as to efficiently extract the spatial features of the current frame. Furthermore, a global spatio-temporal attention module is proposed to fuse the effective hierarchical features from past and future frames to help better deblur the current frame. Another issue that needs to be addressed urgently is the lack of a real-world benchmark dataset. Thus, we contribute a novel dataset (BSD) to the community, by collecting paired blurry/sharp video clips using a co-axis beam splitter acquisition system. Experimental results show that the proposed method (ESTRNN) can achieve better deblurring performance both quantitatively and qualitatively with less computational cost against state-of-the-art video deblurring methods. In addition, cross-validation experiments between datasets illustrate the high generality of BSD over the synthetic datasets. The code and dataset are released at https://github.com/zzh-tech/ESTRNN.","url_abs":"https://arxiv.org/abs/2106.16028v2","url_pdf":"https://arxiv.org/pdf/2106.16028v2.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-spatio-temporal-recurrent-neural-1","repo_url":"https://github.com/zzh-tech/ESTRNN","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"deblurring","task_name":"Deblurring"},{"task_slug":"image-deblurring","task_name":"Image Deblurring"},{"task_slug":"video-deblurring","task_name":"Video Deblurring"}],"methods":[],"datasets_introduced":[{"slug":"beam-splitter-deblurring-bsd","name":"Beam-Splitter Deblurring (BSD)","full_name":"3ms-24ms"}],"methods_introduced":[],"results":[{"leaderboard":"/sota/deblurring-on-beam-splitter-deblurring-bsd","task":"Deblurring","dataset":"Beam-Splitter Deblurring (BSD)","model":"ESTRNN","rank_in_archive_order":3,"of":5,"metrics":{"PSNR":"31.39"},"uses_additional_data":false},{"leaderboard":"/sota/deblurring-on-gopro","task":"Deblurring","dataset":"GoPro","model":"ESTRNN","rank_in_archive_order":48,"of":56,"metrics":{"PSNR":"31.07","SSIM":"0.9023"},"uses_additional_data":true},{"leaderboard":"/sota/image-deblurring-on-gopro","task":"Image Deblurring","dataset":"GoPro","model":"ESTRNN","rank_in_archive_order":45,"of":55,"metrics":{"PSNR":"31.07","SSIM":"0.9023"},"uses_additional_data":true}],"syntology":{"syntology_url":"https://syntology.ai/paper/2106.16028","atlas_url":"https://app.syntology.ai/?focus=2106.16028","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.16028"}},"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/zzh-tech/ESTRNN","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":6,"ran":1,"unverified":1},"by_repo_kind":{"official":{"samples":8,"ran":7,"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":"308d7e741a6c1d7e","entry":"L1","repo":"zzh-tech/ESTRNN","repo_kind":"official","path":"train/loss.py","file_url":"https://github.com/zzh-tech/ESTRNN/blob/HEAD/train/loss.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"308d7e741a6c1d7e"}},{"code_sha256_prefix":"4e215f323ed97be2","entry":"MSE","repo":"zzh-tech/ESTRNN","repo_kind":"official","path":"train/loss.py","file_url":"https://github.com/zzh-tech/ESTRNN/blob/HEAD/train/loss.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4e215f323ed97be2"}},{"code_sha256_prefix":"9bed061f167dd318","entry":"conv1x1","repo":"zzh-tech/ESTRNN","repo_kind":"official","path":"model/arches.py","file_url":"https://github.com/zzh-tech/ESTRNN/blob/HEAD/model/arches.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9bed061f167dd318"}},{"code_sha256_prefix":"f3d374db4177f20c","entry":"conv3x3","repo":"zzh-tech/ESTRNN","repo_kind":"official","path":"model/arches.py","file_url":"https://github.com/zzh-tech/ESTRNN/blob/HEAD/model/arches.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f3d374db4177f20c"}},{"code_sha256_prefix":"05b9fb4be8292106","entry":"conv5x5","repo":"zzh-tech/ESTRNN","repo_kind":"official","path":"model/arches.py","file_url":"https://github.com/zzh-tech/ESTRNN/blob/HEAD/model/arches.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"05b9fb4be8292106"}},{"code_sha256_prefix":"ea472692c3b00532","entry":"feed","repo":"zzh-tech/ESTRNN","repo_kind":"official","path":"model/ESTRNN-RAW.py","file_url":"https://github.com/zzh-tech/ESTRNN/blob/HEAD/model/ESTRNN-RAW.py","link_basis":"plan_row","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ea472692c3b00532"}},{"code_sha256_prefix":"7abfa32a2f1d7424","entry":"logsumexp_2d","repo":"zzh-tech/ESTRNN","repo_kind":"official","path":"model/attention.py","file_url":"https://github.com/zzh-tech/ESTRNN/blob/HEAD/model/attention.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7abfa32a2f1d7424"}},{"code_sha256_prefix":"d5547b4f6d4c8ae9","entry":"Perceptual","repo":"zzh-tech/ESTRNN","repo_kind":"official","path":"train/loss.py","file_url":"https://github.com/zzh-tech/ESTRNN/blob/HEAD/train/loss.py","link_basis":"plan_row","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":"d5547b4f6d4c8ae9"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}