{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/exploiting-optical-flow-guidance-for","title":"Exploiting Optical Flow Guidance for Transformer-Based Video Inpainting","arxiv_id":"2301.10048","date":"2023-01-24","proceeding":null,"authors":["Kaidong Zhang","Jialun Peng","Jingjing Fu","Dong Liu"],"abstract":"Transformers have been widely used for video processing owing to the multi-head self attention (MHSA) mechanism. However, the MHSA mechanism encounters an intrinsic difficulty for video inpainting, since the features associated with the corrupted regions are degraded and incur inaccurate self attention. This problem, termed query degradation, may be mitigated by first completing optical flows and then using the flows to guide the self attention, which was verified in our previous work - flow-guided transformer (FGT). We further exploit the flow guidance and propose FGT++ to pursue more effective and efficient video inpainting. First, we design a lightweight flow completion network by using local aggregation and edge loss. Second, to address the query degradation, we propose a flow guidance feature integration module, which uses the motion discrepancy to enhance the features, together with a flow-guided feature propagation module that warps the features according to the flows. Third, we decouple the transformer along the temporal and spatial dimensions, where flows are used to select the tokens through a temporally deformable MHSA mechanism, and global tokens are combined with the inner-window local tokens through a dual perspective MHSA mechanism. FGT++ is experimentally evaluated to be outperforming the existing video inpainting networks qualitatively and quantitatively.","url_abs":"https://arxiv.org/abs/2301.10048v2","url_pdf":"https://arxiv.org/pdf/2301.10048v2.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":"exploiting-optical-flow-guidance-for","repo_url":"https://github.com/hitachinsk/fgt","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"exploiting-optical-flow-guidance-for","repo_url":"https://github.com/hitachinsk/isvi","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"optical-flow-estimation","task_name":"Optical Flow Estimation"},{"task_slug":"video-inpainting","task_name":"Video Inpainting"}],"methods":[{"method_slug":"pixel-prediction","method_name":"Inpainting"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/video-inpainting-on-davis","task":"Video Inpainting","dataset":"DAVIS","model":"FGT++","rank_in_archive_order":10,"of":11,"metrics":{"LPIPS (object)":"0.035","LPIPS (square)":"0.028","PNSR (object)":"35.61","SSIM (object)":"0.961","SSIM (square)":"0.971"},"uses_additional_data":false},{"leaderboard":"/sota/video-inpainting-on-davis","task":"Video Inpainting","dataset":"DAVIS","model":"FGT++*","rank_in_archive_order":11,"of":11,"metrics":{"LPIPS (object)":"0.027","LPIPS (square)":"0.022","PNSR (object)":"35.9","SSIM (object)":"96.8","SSIM (square)":"97.6"},"uses_additional_data":false},{"leaderboard":"/sota/video-inpainting-on-youtube-vos-1","task":"Video Inpainting","dataset":"YouTube-VOS","model":"FGT++","rank_in_archive_order":1,"of":2,"metrics":{"LPIPS":"0.025","PSNR":"35.02","PSNR (square)":"33.18","SSIM":"97.6"},"uses_additional_data":false},{"leaderboard":"/sota/video-inpainting-on-youtube-vos-1","task":"Video Inpainting","dataset":"YouTube-VOS","model":"FGT++*","rank_in_archive_order":2,"of":2,"metrics":{"LPIPS":"0.022","PSNR":"35.36","PSNR (square)":"33.72","SSIM":"97.8"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2301.10048","atlas_url":"https://app.syntology.ai/?focus=2301.10048","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2301.10048"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2301.10048\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2301.10048"},"call":"get_concepts_for_paper(arxiv_id=\"2301.10048\")"}],"by_repo":[{"repo":"hitachinsk/fgt","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2208.06768"],"harvested_for_calls":[{"arxiv_id":"2208.06768","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2208.06768"},"call":"get_harvested_code_for_paper(arxiv_id=\"2208.06768\")"}]},{"repo":"hitachinsk/isvi","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"b6fff5553a1fd5fe13269ab947b81270dc302ce15da12d5f96a4324db1d08b00","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}