GraphVid: Interactive Graph-Controllable Video Generation (ECCV'26)</p>\n","updatedAt":"2026-07-24T02:18:42.673Z","author":{"_id":"678ac3b31cbaa0b4bc295885","avatarUrl":"/avatars/1244fc1b305c9c6383df9bb5e4707347.svg","fullname":"Ismini Lourentzou","name":"isminoula","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":1,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.5098852515220642},"editors":["isminoula"],"editorAvatarUrls":["/avatars/1244fc1b305c9c6383df9bb5e4707347.svg"],"reactions":[],"isReport":false}}],"primaryEmailConfirmed":false,"paper":{"id":"2607.21580","authors":[{"_id":"6a62caea2ee212ed0e2a1468","name":"Vedant Shah","hidden":false},{"_id":"6a62caea2ee212ed0e2a1469","name":"Onkar Susladkar","hidden":false},{"_id":"6a62caea2ee212ed0e2a146a","name":"Tushar Prakash","hidden":false},{"_id":"6a62caea2ee212ed0e2a146b","name":"Kiet Nguyen","hidden":false},{"_id":"6a62caea2ee212ed0e2a146c","name":"Tianjio Yu","hidden":false},{"_id":"6a62caea2ee212ed0e2a146d","name":"Adheesh Juvekar","hidden":false},{"_id":"6a62caea2ee212ed0e2a146e","name":"Muntasir Waheed","hidden":false},{"_id":"6a62caea2ee212ed0e2a146f","name":"Ismini Lourentzou","hidden":false}],"publishedAt":"2026-07-23T00:00:00.000Z","submittedOnDailyAt":"2026-07-24T00:00:00.000Z","title":"GraphVid: Interactive Graph-Controllable Video Generation","submittedOnDailyBy":{"_id":"678ac3b31cbaa0b4bc295885","avatarUrl":"/avatars/1244fc1b305c9c6383df9bb5e4707347.svg","isPro":false,"fullname":"Ismini Lourentzou","user":"isminoula","type":"user","name":"isminoula"},"summary":"Controllable video generation remains challenging due to the difficulty of specifying precise multi-object interactions using text prompts or motion-control inputs that primarily constrain pixel movement. In practice, trajectory-based control often requires users to draw accurate tracks for multiple objects, which scales poorly with scene complexity and becomes ambiguous under occlusion or overlap. To enable flexible yet precise multi-subject control, we introduce GraphVid, a graph-conditioned image-to-video generation model that enables interactive control through structured interaction graphs. We further curate GraphVid-Bench, a large-scale interaction-centric video dataset with structured relational annotations to enable training of interaction-aware video generation models. Despite using substantially less training data and fewer trainable parameters than prior motion-control methods, GraphVid delivers strong controllability and video quality. Compared with Motion-I2V, GraphVid reduces FID by up to 39.9% and FVD by 37.6%, while improving PSNR (9.87=>15.98) and SSIM (0.38=>0.61). Our results highlight the potential of structured semantic interfaces as a powerful paradigm for controllable video generation.","upvotes":2,"discussionId":"6a62caea2ee212ed0e2a1470","projectPage":"https://plan-lab.github.io/projects/graphvid","organization":{"_id":"681be082cdcffc26982f55d7","name":"PLAN-Lab","fullname":"PLAN Lab @University of Illinois Urbana-Champaign","avatar":"https://cdn-avatars.huggingface.co/v1/production/uploads/678ac3b31cbaa0b4bc295885/B6lcdzr22Y44SsFuyTnwH.jpeg"}},"canReadDatabase":false,"canManagePapers":false,"canSubmit":false,"hasHfLevelAccess":false,"upvoted":false,"upvoters":[{"_id":"620783f24e28382272337ba4","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/620783f24e28382272337ba4/zkUveQPNiDfYjgGhuFErj.jpeg","isPro":false,"fullname":"GuoLiangTang","user":"Tommy930","type":"user"},{"_id":"6a14769a210a78332f6696be","avatarUrl":"/avatars/f0b77e7a96590ad8da4f091c751200be.svg","isPro":false,"fullname":"梁千怡","user":"danieldavisgo","type":"user"}],"acceptLanguages":["en"],"dailyPaperRank":0,"organization":{"_id":"681be082cdcffc26982f55d7","name":"PLAN-Lab","fullname":"PLAN Lab @University of Illinois Urbana-Champaign","avatar":"https://cdn-avatars.huggingface.co/v1/production/uploads/678ac3b31cbaa0b4bc295885/B6lcdzr22Y44SsFuyTnwH.jpeg"},"query":{}}">
GraphVid: Interactive Graph-Controllable Video Generation
Abstract
Controllable video generation remains challenging due to the difficulty of specifying precise multi-object interactions using text prompts or motion-control inputs that primarily constrain pixel movement. In practice, trajectory-based control often requires users to draw accurate tracks for multiple objects, which scales poorly with scene complexity and becomes ambiguous under occlusion or overlap. To enable flexible yet precise multi-subject control, we introduce GraphVid, a graph-conditioned image-to-video generation model that enables interactive control through structured interaction graphs. We further curate GraphVid-Bench, a large-scale interaction-centric video dataset with structured relational annotations to enable training of interaction-aware video generation models. Despite using substantially less training data and fewer trainable parameters than prior motion-control methods, GraphVid delivers strong controllability and video quality. Compared with Motion-I2V, GraphVid reduces FID by up to 39.9% and FVD by 37.6%, while improving PSNR (9.87=>15.98) and SSIM (0.38=>0.61). Our results highlight the potential of structured semantic interfaces as a powerful paradigm for controllable video generation.
Community
GraphVid: Interactive Graph-Controllable Video Generation (ECCV'26)
Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.
Tap or paste here to upload images
Cite arxiv.org/abs/2607.21580 in a model README.md to link it from this page.
Cite arxiv.org/abs/2607.21580 in a dataset README.md to link it from this page.
Cite arxiv.org/abs/2607.21580 in a Space README.md to link it from this page.
Discussion (0)
Sign in to join the discussion. Free account, 30 seconds — email code or GitHub.
Sign in →No comments yet. Sign in and be the first to say something.