{"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/few-shot-video-to-video-synthesis","title":"Few-shot Video-to-Video Synthesis","arxiv_id":"1910.12713","date":"2019-10-28","proceeding":"NeurIPS 2019 12","authors":["Ting-Chun Wang","Ming-Yu Liu","Andrew Tao","Guilin Liu","Jan Kautz","Bryan Catanzaro"],"abstract":"Video-to-video synthesis (vid2vid) aims at converting an input semantic video, such as videos of human poses or segmentation masks, to an output photorealistic video. While the state-of-the-art of vid2vid has advanced significantly, existing approaches share two major limitations. First, they are data-hungry. Numerous images of a target human subject or a scene are required for training. Second, a learned model has limited generalization capability. A pose-to-human vid2vid model can only synthesize poses of the single person in the training set. It does not generalize to other humans that are not in the training set. To address the limitations, we propose a few-shot vid2vid framework, which learns to synthesize videos of previously unseen subjects or scenes by leveraging few example images of the target at test time. Our model achieves this few-shot generalization capability via a novel network weight generation module utilizing an attention mechanism. We conduct extensive experimental validations with comparisons to strong baselines using several large-scale video datasets including human-dancing videos, talking-head videos, and street-scene videos. The experimental results verify the effectiveness of the proposed framework in addressing the two limitations of existing vid2vid approaches.","url_abs":"https://arxiv.org/abs/1910.12713v1","url_pdf":"https://arxiv.org/pdf/1910.12713v1.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":"few-shot-video-to-video-synthesis","repo_url":"https://github.com/FredMusoro/few-few","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"few-shot-video-to-video-synthesis","repo_url":"https://github.com/NVlabs/few-shot-vid2vid","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"few-shot-video-to-video-synthesis","repo_url":"https://github.com/achen353/imaginaire-fsvid2vid","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"few-shot-video-to-video-synthesis","repo_url":"https://github.com/k4rth33k/vid_to_vid_python3","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"few-shot-video-to-video-synthesis","repo_url":"https://github.com/livingbio/fewshot-vid2vid","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"few-shot-video-to-video-synthesis","repo_url":"https://github.com/rickyHong/few-shot-vid2vid-repl","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"video-to-video-synthesis","task_name":"Video-to-Video Synthesis"}],"methods":[{"method_slug":"test","method_name":"Test"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/video-to-video-synthesis-on-street-scene","task":"Video-to-Video Synthesis","dataset":"Street Scene","model":"Few-shot Video-to-Video","rank_in_archive_order":1,"of":1,"metrics":{"FID":"144.24"},"uses_additional_data":false},{"leaderboard":"/sota/video-to-video-synthesis-on-youtube-dancing","task":"Video-to-Video Synthesis","dataset":"YouTube Dancing","model":"Few-shot Video-to-Video","rank_in_archive_order":1,"of":1,"metrics":{"FID":"80.44"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1910.12713","atlas_url":"https://app.syntology.ai/?focus=1910.12713","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":"1910.12713"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1910.12713\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1910.12713"},"call":"get_concepts_for_paper(arxiv_id=\"1910.12713\")"}],"by_repo":[{"repo":"FredMusoro/few-few","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"NVlabs/few-shot-vid2vid","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"achen353/imaginaire-fsvid2vid","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"k4rth33k/vid_to_vid_python3","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"livingbio/fewshot-vid2vid","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"rickyHong/few-shot-vid2vid-repl","kind":"listed","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":"ecf8166660e72ed50a0dfcba0dea5075823c33b4880f75d15d4e35c2bf06b2e6","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}