{"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/flow-guided-sparse-transformer-for-video","title":"Flow-Guided Sparse Transformer for Video Deblurring","arxiv_id":"2201.01893","date":"2022-01-06","proceeding":null,"authors":["Jing Lin","Yuanhao Cai","Xiaowan Hu","Haoqian Wang","Youliang Yan","Xueyi Zou","Henghui Ding","Yulun Zhang","Radu Timofte","Luc van Gool"],"abstract":"Exploiting similar and sharper scene patches in spatio-temporal neighborhoods is critical for video deblurring. However, CNN-based methods show limitations in capturing long-range dependencies and modeling non-local self-similarity. In this paper, we propose a novel framework, Flow-Guided Sparse Transformer (FGST), for video deblurring. In FGST, we customize a self-attention module, Flow-Guided Sparse Window-based Multi-head Self-Attention (FGSW-MSA). For each $query$ element on the blurry reference frame, FGSW-MSA enjoys the guidance of the estimated optical flow to globally sample spatially sparse yet highly related $key$ elements corresponding to the same scene patch in neighboring frames. Besides, we present a Recurrent Embedding (RE) mechanism to transfer information from past frames and strengthen long-range temporal dependencies. Comprehensive experiments demonstrate that our proposed FGST outperforms state-of-the-art (SOTA) methods on both DVD and GOPRO datasets and even yields more visually pleasing results in real video deblurring. Code and pre-trained models are publicly available at https://github.com/linjing7/VR-Baseline","url_abs":"https://arxiv.org/abs/2201.01893v3","url_pdf":"https://arxiv.org/pdf/2201.01893v3.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":"flow-guided-sparse-transformer-for-video","repo_url":"https://github.com/linjing7/VR-Baseline","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"deblurring","task_name":"Deblurring"},{"task_slug":"optical-flow-estimation","task_name":"Optical Flow Estimation"},{"task_slug":"video-deblurring","task_name":"Video Deblurring"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"attention-dropout","method_name":"Attention Dropout"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"cosine-annealing","method_name":"Cosine Annealing"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"linear-warmup-with-cosine-annealing","method_name":"Linear Warmup With Cosine Annealing"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"sparse-transformer","method_name":"Sparse Transformer"},{"method_slug":"transformer","method_name":"Transformer"},{"method_slug":"weight-decay","method_name":"Weight Decay"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/deblurring-on-dvd","task":"Deblurring","dataset":"DVD","model":"FGST","rank_in_archive_order":1,"of":3,"metrics":{"PSNR":"33.03"},"uses_additional_data":false},{"leaderboard":"/sota/deblurring-on-dvd-1","task":"Deblurring","dataset":"DVD","model":"FGST","rank_in_archive_order":5,"of":7,"metrics":{"PSNR":"33.50"},"uses_additional_data":false},{"leaderboard":"/sota/deblurring-on-gopro","task":"Deblurring","dataset":"GoPro","model":"FGST","rank_in_archive_order":26,"of":56,"metrics":{"PSNR":"33.03","SSIM":"0.964"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2201.01893","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2201.01893"}},"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":"deterministic:regex_extraction","url":"https://github.com/linjing7/VR-Baseline","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran_fixture":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":0,"samples":[{"code_sha256_prefix":"3c53e8fbf0324a31","entry":"Forward","repo":"linjing7/vr-baseline","repo_kind":"official","path":"mmedit/models/backbones/sr_backbones/FGST.py","file_url":"https://github.com/linjing7/vr-baseline/blob/HEAD/mmedit/models/backbones/sr_backbones/FGST.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"3c53e8fbf0324a31"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}