Project Page: <a href=\"https://miniz233.github.io/MotionBeyondMorphology/\" rel=\"nofollow\">https://miniz233.github.io/MotionBeyondMorphology/</a><br>Github: <a href=\"https://github.com/miniz233/MBM\" rel=\"nofollow\">https://github.com/miniz233/MBM</a></p>\n","updatedAt":"2026-08-04T06:04:49.140Z","author":{"_id":"65e67be231de1c098be18f5f","avatarUrl":"/avatars/1dfc363140f5161d8b06ba0ad948530b.svg","fullname":"Zhimin Zhang","name":"zmmm","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.511471152305603},"editors":["zmmm"],"editorAvatarUrls":["/avatars/1dfc363140f5161d8b06ba0ad948530b.svg"],"reactions":[],"isReport":false}},{"id":"6a7181e36f0f79b6d4decd50","author":{"_id":"65e67be231de1c098be18f5f","avatarUrl":"/avatars/1dfc363140f5161d8b06ba0ad948530b.svg","fullname":"Zhimin Zhang","name":"zmmm","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"isUserFollowing":false},"createdAt":"2026-08-04T06:08:35.000Z","type":"comment","data":{"edited":false,"hidden":false,"latest":{"raw":"Morphology-Adaptive Motion Transfer (Image2Video)\nhttps://cdn-uploads.huggingface.co/production/uploads/65e67be231de1c098be18f5f/ODyrckL4k5yudUrzwEIOW.mp4\nhttps://cdn-uploads.huggingface.co/production/uploads/65e67be231de1c098be18f5f/LFUtTdfZ4HpbNXorAInlV.mp4\n","html":"<p>Morphology-Adaptive Motion Transfer (Image2Video)</p>\n<p><video src=\"https://cdn-uploads.huggingface.co/production/uploads/65e67be231de1c098be18f5f/ODyrckL4k5yudUrzwEIOW.mp4\" controls=\"\" class=\"max-w-full!\"></video></p>\n<p><video src=\"https://cdn-uploads.huggingface.co/production/uploads/65e67be231de1c098be18f5f/LFUtTdfZ4HpbNXorAInlV.mp4\" controls=\"\" class=\"max-w-full!\"></video></p>\n","updatedAt":"2026-08-04T06:08:35.465Z","author":{"_id":"65e67be231de1c098be18f5f","avatarUrl":"/avatars/1dfc363140f5161d8b06ba0ad948530b.svg","fullname":"Zhimin Zhang","name":"zmmm","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.49161556363105774},"editors":["zmmm"],"editorAvatarUrls":["/avatars/1dfc363140f5161d8b06ba0ad948530b.svg"],"reactions":[],"isReport":false}},{"id":"6a7187b43a1162e760c696ef","author":{"_id":"65e67be231de1c098be18f5f","avatarUrl":"/avatars/1dfc363140f5161d8b06ba0ad948530b.svg","fullname":"Zhimin Zhang","name":"zmmm","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"isUserFollowing":false},"createdAt":"2026-08-04T06:33:24.000Z","type":"comment","data":{"edited":false,"hidden":false,"latest":{"raw":"🚀 We introduce **Motion Beyond Morphology (MBM)**, a framework for transferring motion across objects with substantially different morphologies, without relying on fixed structural correspondence.\n\nMBM learns complementary multi-granularity abstract motion representations to bootstrap cross-category supervision, and then enables direct reference-video-conditioned generation at inference. Experiments across Same, Near, and Far category gaps demonstrate state-of-the-art motion fidelity and target preservation.\n\n🌐 Project page: https://miniz233.github.io/MotionBeyondMorphology/\n💻 Code: https://github.com/miniz233/MBM","html":"<p>🚀 We introduce <strong>Motion Beyond Morphology (MBM)</strong>, a framework for transferring motion across objects with substantially different morphologies, without relying on fixed structural correspondence.</p>\n<p>MBM learns complementary multi-granularity abstract motion representations to bootstrap cross-category supervision, and then enables direct reference-video-conditioned generation at inference. Experiments across Same, Near, and Far category gaps demonstrate state-of-the-art motion fidelity and target preservation.</p>\n<p>🌐 Project page: <a href=\"https://miniz233.github.io/MotionBeyondMorphology/\" rel=\"nofollow\">https://miniz233.github.io/MotionBeyondMorphology/</a><br>💻 Code: <a href=\"https://github.com/miniz233/MBM\" rel=\"nofollow\">https://github.com/miniz233/MBM</a></p>\n","updatedAt":"2026-08-04T06:33:24.688Z","author":{"_id":"65e67be231de1c098be18f5f","avatarUrl":"/avatars/1dfc363140f5161d8b06ba0ad948530b.svg","fullname":"Zhimin Zhang","name":"zmmm","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.7434152960777283},"editors":["zmmm"],"editorAvatarUrls":["/avatars/1dfc363140f5161d8b06ba0ad948530b.svg"],"reactions":[],"isReport":false}}],"primaryEmailConfirmed":false,"paper":{"id":"2608.01628","authors":[{"_id":"6a715e4aec5082b9f872ce74","name":"Zhixue Fang","hidden":false},{"_id":"6a715e4aec5082b9f872ce75","name":"Zhimin Zhang","hidden":false},{"_id":"6a715e4aec5082b9f872ce76","name":"Bi'an Du","hidden":false},{"_id":"6a715e4aec5082b9f872ce77","name":"Zijie Meng","hidden":false},{"_id":"6a715e4aec5082b9f872ce78","name":"Yan Zhou","hidden":false},{"_id":"6a715e4aec5082b9f872ce79","name":"Wei Hu","hidden":false},{"_id":"6a715e4aec5082b9f872ce7a","name":"Guoxin Zhang","hidden":false},{"_id":"6a715e4aec5082b9f872ce7b","name":"Pengfei Wan","hidden":false},{"_id":"6a715e4aec5082b9f872ce7c","name":"Kun Gai","hidden":false}],"mediaUrls":["https://cdn-uploads.huggingface.co/production/uploads/65e67be231de1c098be18f5f/osTB9STm0VcQxeUBOnIZN.mp4","https://cdn-uploads.huggingface.co/production/uploads/65e67be231de1c098be18f5f/FIXMTR99dY6E2b1MfwgVI.mp4"],"publishedAt":"2026-08-03T00:00:00.000Z","submittedOnDailyAt":"2026-08-04T00:00:00.000Z","title":"Motion Beyond Morphology: Bootstrapping Cross-Category Motion Transfer from Abstract Motion Representations","submittedOnDailyBy":{"_id":"65e67be231de1c098be18f5f","avatarUrl":"/avatars/1dfc363140f5161d8b06ba0ad948530b.svg","isPro":false,"fullname":"Zhimin Zhang","user":"zmmm","type":"user","name":"zmmm"},"summary":"Video motion transfer aims to animate a target object using dynamics from a reference video. Existing formulations largely rely on fixed structural correspondence, which becomes ill-defined when reference and target objects differ substantially in morphology, articulation, or deformation mechanisms. We introduce Motion Beyond Morphology, a perspective that seeks to transfer motion beyond fixed structural correspondence, by preserving dynamics that remain meaningful across different target morphologies. To realize this, we propose a two-stage framework. Stage~I learns complementary multi-granularity abstract motion views and uses them to bootstrap cross-category video pairs that preserve transferable dynamics across diverse morphologies. Stage~II internalizes this supervision into direct reference-video-conditioned generation, removing the need for explicit motion extraction at inference. We further introduce OpenVMT-Dataset and OpenVMT-Bench for training and evaluating image- and text-conditioned motion transfer across Same, Near, and Far category gaps, and plan to release both upon acceptance. Extensive experiments demonstrate state-of-the-art motion fidelity and target preservation. Project page: https://miniz233.github.io/MotionBeyondMorphology/","upvotes":10,"discussionId":"6a715e4aec5082b9f872ce7d","projectPage":"https://miniz233.github.io/MotionBeyondMorphology/","githubRepo":"https://github.com/miniz233/MBM","githubRepoAddedBy":"user","githubStars":0,"organization":{"_id":"662c559b322afcbae51b3c8b","name":"KlingTeam","fullname":"Kling Team","avatar":"https://cdn-avatars.huggingface.co/v1/production/uploads/60e272ca6c78a8c122b12127/ZQV1aKLUDPf2rUcxxAqj6.jpeg"}},"canReadDatabase":false,"canManagePapers":false,"canSubmit":false,"hasHfLevelAccess":false,"upvoted":false,"upvoters":[{"_id":"65e67be231de1c098be18f5f","avatarUrl":"/avatars/1dfc363140f5161d8b06ba0ad948530b.svg","isPro":false,"fullname":"Zhimin Zhang","user":"zmmm","type":"user"},{"_id":"66309c300c0c122b688c779f","avatarUrl":"/avatars/eae3e50910120e8899912833ba15ecc7.svg","isPro":false,"fullname":"Zhixue Fang","user":"fffzx","type":"user"},{"_id":"6507fbecffc738079ca592bf","avatarUrl":"/avatars/1cb0f39ac6dc2dba2292846a8d7746da.svg","isPro":false,"fullname":"Ming Chen","user":"ChenMing-thu14","type":"user"},{"_id":"64e57e521412b511e4388310","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/64e57e521412b511e4388310/1DL-B1TJL9jEcnsy4N_46.jpeg","isPro":false,"fullname":"Shujuan Li","user":"lisj575","type":"user"},{"_id":"6347aca88af48bc2fb5416c5","avatarUrl":"/avatars/ee56e7985599314c6c7076300dbde884.svg","isPro":false,"fullname":"Wang Qiulin","user":"Qiulin","type":"user"},{"_id":"65f30652b0d359b2ffa4a42c","avatarUrl":"/avatars/f6cb0705b25cc0ccc0b099811ef9a871.svg","isPro":false,"fullname":"zrx","user":"z-rx","type":"user"},{"_id":"641aa705fb5ffff5ac7b4d1f","avatarUrl":"/avatars/088fac98c75d019e5b6bfb289886db0f.svg","isPro":false,"fullname":"SanGibb","user":"SanGibb","type":"user"},{"_id":"663d788275dc22df1e6792f7","avatarUrl":"/avatars/5f8eada02ec4d658418e140007c5c9b8.svg","isPro":false,"fullname":"Ma","user":"Miles629","type":"user"},{"_id":"6334054ae5e52bbbf5f7e63d","avatarUrl":"/avatars/8ab228b5eba48336ff032c1011459885.svg","isPro":false,"fullname":"lsf","user":"lsfhuihuiff","type":"user"},{"_id":"64ba7a73a01da43118fce871","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/64ba7a73a01da43118fce871/x2QDw6N8QRZkwwYOLNLYD.png","isPro":false,"fullname":"YuchuanTian","user":"yuchuantian","type":"user"}],"acceptLanguages":["en"],"dailyPaperRank":0,"organization":{"_id":"662c559b322afcbae51b3c8b","name":"KlingTeam","fullname":"Kling Team","avatar":"https://cdn-avatars.huggingface.co/v1/production/uploads/60e272ca6c78a8c122b12127/ZQV1aKLUDPf2rUcxxAqj6.jpeg"},"markdownContentUrl":"https://huggingface.co/buckets/huggingchat/papers-content/resolve/2608/2608.01628.md","query":{}}">

Get this paper in your agent:

Don't have the latest CLI?

Cite arxiv.org/abs/2608.01628 in a model README.md to link it from this page.

Cite arxiv.org/abs/2608.01628 in a dataset README.md to link it from this page.

Cite arxiv.org/abs/2608.01628 in a Space README.md to link it from this page.

Add this paper to a collection to link it from this page.