{"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/elevating-flow-guided-video-inpainting-with","title":"Elevating Flow-Guided Video Inpainting with Reference Generation","arxiv_id":"2412.08975","date":"2024-12-12","proceeding":null,"authors":["Suhwan Cho","Seoung Wug Oh","Sangyoun Lee","Joon-Young Lee"],"abstract":"Video inpainting (VI) is a challenging task that requires effective propagation of observable content across frames while simultaneously generating new content not present in the original video. In this study, we propose a robust and practical VI framework that leverages a large generative model for reference generation in combination with an advanced pixel propagation algorithm. Powered by a strong generative model, our method not only significantly enhances frame-level quality for object removal but also synthesizes new content in the missing areas based on user-provided text prompts. For pixel propagation, we introduce a one-shot pixel pulling method that effectively avoids error accumulation from repeated sampling while maintaining sub-pixel precision. To evaluate various VI methods in realistic scenarios, we also propose a high-quality VI benchmark, HQVI, comprising carefully generated videos using alpha matte composition. On public benchmarks and the HQVI dataset, our method demonstrates significantly higher visual quality and metric scores compared to existing solutions. Furthermore, it can process high-resolution videos exceeding 2K resolution with ease, underscoring its superiority for real-world applications.","url_abs":"https://arxiv.org/abs/2412.08975v1","url_pdf":"https://arxiv.org/pdf/2412.08975v1.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":"elevating-flow-guided-video-inpainting-with","repo_url":"https://github.com/suhwan-cho/RGVI","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"2k","task_name":"2k"},{"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-hqvi-240p","task":"Video Inpainting","dataset":"HQVI (240p)","model":"RGVI","rank_in_archive_order":1,"of":7,"metrics":{"LPIPS":"0.0335","PSNR":"30.66","SSIM":"0.9527","VFID":"0.1825"},"uses_additional_data":false},{"leaderboard":"/sota/video-inpainting-on-hqvi-240p","task":"Video Inpainting","dataset":"HQVI (240p)","model":"RGVI w/o Ref.","rank_in_archive_order":3,"of":7,"metrics":{"LPIPS":"0.0390","PSNR":"31.60","SSIM":"0.9559","VFID":"0.1868"},"uses_additional_data":false},{"leaderboard":"/sota/video-inpainting-on-hqvi-2k","task":"Video Inpainting","dataset":"HQVI (2K)","model":"RGVI","rank_in_archive_order":1,"of":2,"metrics":{"LPIPS":"0.0357","PSNR":"30.10","SSIM":"0.9489","VFID":"0.0058"},"uses_additional_data":false},{"leaderboard":"/sota/video-inpainting-on-hqvi-2k","task":"Video Inpainting","dataset":"HQVI (2K)","model":"RGVI w/o Ref.","rank_in_archive_order":2,"of":2,"metrics":{"LPIPS":"0.0403","PSNR":"29.81","SSIM":"0.9501","VFID":"0.0101"},"uses_additional_data":false},{"leaderboard":"/sota/video-inpainting-on-hqvi-480p","task":"Video Inpainting","dataset":"HQVI (480p)","model":"RGVI","rank_in_archive_order":1,"of":4,"metrics":{"LPIPS":"0.0342","PSNR":"30.90","SSIM":"0.9513","VFID":"0.0311"},"uses_additional_data":false},{"leaderboard":"/sota/video-inpainting-on-hqvi-480p","task":"Video Inpainting","dataset":"HQVI (480p)","model":"RGVI w/o Ref.","rank_in_archive_order":3,"of":4,"metrics":{"LPIPS":"0.0403","PSNR":"31.19","SSIM":"0.9534","VFID":"0.0404"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2412.08975","atlas_url":"https://app.syntology.ai/?focus=2412.08975","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":"2412.08975"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2412.08975\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2412.08975"},"call":"get_concepts_for_paper(arxiv_id=\"2412.08975\")"}],"by_repo":[{"repo":"suhwan-cho/RGVI","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0}],"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":"4ae212fc215f60ca5d78b14b7331dba22cf4c7b415eebec58ec0bcb900c62e24","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}