While Video Virtual Try-on (VVT) has achieved remarkable progress in synthesizing realistic garment overlays on dynamic subjects, existing paradigms remains fundamentally constrained by a passive dependency on source camera trajectories, failing to accommodate the requisite interactive freedom for omnidirectional viewpoint exploration. To address this limitation, we define a pioneering research frontier: Camera-controllable Video Virtual Try-on (CaM-VVT). Unlike conventional VVT, CaM-VVT not only necessitates viewpoint-agnostic texture hallucination but also strict structural synchronization between non-rigid human dynamics and background contexts under arbitrary, unconstrained camera movements. To tackle these challenges, we present TryOnCrafter, the first unified DiT-based framework specifically architected for the CaM-VVT task. Departing from implicit pixel-space manipulation, we introduce a Renderable 4D Try-on Proxy that explicitly decouples the human subject from the environment. This is achieved by distilling high-fidelity 2D try-on priors into a clothed 3DGS-based avatar, which is subsequently animated via SMPL-X sequences and metric-aligned into a reconstructed background point cloud. This proxy establishes a robust structural foundation with superior texture density and motion integrity. Our Proxy-Anchored Video DiT leverages this robust structural foundation as a primary geometric anchor, ensuring that the synthesized photorealistic videos are strictly constrained by prescribed trajectories and physically plausible deformations. Benefiting from the inherent editability of the 4D proxy, TryOnCrafter facilitates diverse downstream applications, including human relocalization, ``bullet time'' effects, and 360-degree orbital viewing.</p>\n","updatedAt":"2026-06-25T03:29:51.386Z","author":{"_id":"65519eb532f278f503b3b2c3","avatarUrl":"/avatars/2e180f7b20189cd2d8a75e05c2913c5d.svg","fullname":"lalala","name":"QuanjianSong","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":2,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.8487952947616577},"editors":["QuanjianSong"],"editorAvatarUrls":["/avatars/2e180f7b20189cd2d8a75e05c2913c5d.svg"],"reactions":[],"isReport":false}}],"primaryEmailConfirmed":false,"paper":{"id":"2606.26092","authors":[{"_id":"6a3c9804f3facdb67e9ff0d5","name":"Hao Sun","hidden":false},{"_id":"6a3c9804f3facdb67e9ff0d6","name":"Hao Yan","hidden":false},{"_id":"6a3c9804f3facdb67e9ff0d7","name":"Mengting Chen","hidden":false},{"_id":"6a3c9804f3facdb67e9ff0d8","name":"Quanjian Song","hidden":false},{"_id":"6a3c9804f3facdb67e9ff0d9","name":"Yu Li","hidden":false},{"_id":"6a3c9804f3facdb67e9ff0da","name":"Juan Cao","hidden":false},{"_id":"6a3c9804f3facdb67e9ff0db","name":"Jinsong Lan","hidden":false},{"_id":"6a3c9804f3facdb67e9ff0dc","name":"Xiaoyong Zhu","hidden":false},{"_id":"6a3c9804f3facdb67e9ff0dd","name":"Bo Zheng","hidden":false},{"_id":"6a3c9804f3facdb67e9ff0de","name":"Sheng Tang","hidden":false}],"publishedAt":"2026-06-24T00:00:00.000Z","submittedOnDailyAt":"2026-06-25T00:00:00.000Z","title":"TryOnCrafter: Unleashing Camera Trajectories for Realistic Video Virtual Try-on via a Renderable 4D Try-on Proxy","submittedOnDailyBy":{"_id":"65519eb532f278f503b3b2c3","avatarUrl":"/avatars/2e180f7b20189cd2d8a75e05c2913c5d.svg","isPro":false,"fullname":"lalala","user":"QuanjianSong","type":"user","name":"QuanjianSong"},"summary":"While Video Virtual Try-on (VVT) has achieved remarkable progress in synthesizing realistic garment overlays on dynamic subjects, existing paradigms remains fundamentally constrained by a passive dependency on source camera trajectories, failing to accommodate the requisite interactive freedom for omnidirectional viewpoint exploration. To address this limitation, we define a pioneering research frontier: Camera-controllable Video Virtual Try-on (CaM-VVT). Unlike conventional VVT, CaM-VVT not only necessitates viewpoint-agnostic texture hallucination but also strict structural synchronization between non-rigid human dynamics and background contexts under arbitrary, unconstrained camera movements. To tackle these challenges, we present TryOnCrafter, the first unified DiT-based framework specifically architected for the CaM-VVT task. Departing from implicit pixel-space manipulation, we introduce a Renderable 4D Try-on Proxy that explicitly decouples the human subject from the environment. This is achieved by distilling high-fidelity 2D try-on priors into a clothed 3DGS-based avatar, which is subsequently animated via SMPL-X sequences and metric-aligned into a reconstructed background point cloud. This proxy establishes a robust structural foundation with superior texture density and motion integrity. Our Proxy-Anchored Video DiT leverages this robust structural foundation as a primary geometric anchor, ensuring that the synthesized photorealistic videos are strictly constrained by prescribed trajectories and physically plausible deformations. Benefiting from the inherent editability of the 4D proxy, TryOnCrafter facilitates diverse downstream applications, including human relocalization, ``bullet time'' effects, and 360-degree orbital viewing.","upvotes":5,"discussionId":"6a3c9805f3facdb67e9ff0df","ai_summary":"Camera-controllable video virtual try-on framework uses a 4D proxy with explicit human-environment decoupling and DiT-based video generation for omnidirectional viewing.","ai_keywords":["Video Virtual Try-on","DiT-based framework","4D proxy","3DGS-based avatar","SMPL-X sequences","background point cloud","photorealistic video synthesis","geometric anchor","structural synchronization","viewpoint-agnostic texture hallucination"],"ai_summary_model":"Qwen/Qwen2.5-Coder-32B-Instruct","organization":{"_id":"6a1e77a8a56da3965b2deafe","name":"alibaba-inc","fullname":"Alibaba-Inc","avatar":"https://cdn-avatars.huggingface.co/v1/production/uploads/651ac1ab28c2633de9600a76/XYWJ3OF5G3cAMf3Q0h3EF.png"}},"canReadDatabase":false,"canManagePapers":false,"canSubmit":false,"hasHfLevelAccess":false,"upvoted":false,"upvoters":[{"_id":"65519eb532f278f503b3b2c3","avatarUrl":"/avatars/2e180f7b20189cd2d8a75e05c2913c5d.svg","isPro":false,"fullname":"lalala","user":"QuanjianSong","type":"user"},{"_id":"68639a200b262058aa4b44cc","avatarUrl":"/avatars/b3f94124fcfd0a3d86e9db1da9a2b608.svg","isPro":false,"fullname":"Hao Sun","user":"sunhao242","type":"user"},{"_id":"6661ad9bc229e1da8e9b939d","avatarUrl":"/avatars/45d83ebdc1a2fc027309eb28f2584ef2.svg","isPro":false,"fullname":"chen","user":"mathildachen","type":"user"},{"_id":"697cd4971cac2994a79540f8","avatarUrl":"/avatars/61dc9e371c165a8f867eb1ef360f2269.svg","isPro":false,"fullname":"Jay CHOU","user":"zhoujieluno1","type":"user"},{"_id":"68a3eeb57aca8caa6e9ba41c","avatarUrl":"/avatars/692b066b41d99fc14a7c72226ed2cdc7.svg","isPro":false,"fullname":"JasonCocomo","user":"JasonCocomo001","type":"user"}],"acceptLanguages":["en"],"dailyPaperRank":0,"organization":{"_id":"6a1e77a8a56da3965b2deafe","name":"alibaba-inc","fullname":"Alibaba-Inc","avatar":"https://cdn-avatars.huggingface.co/v1/production/uploads/651ac1ab28c2633de9600a76/XYWJ3OF5G3cAMf3Q0h3EF.png"},"markdownContentUrl":"https://huggingface.co/buckets/huggingchat/papers-content/resolve/2606/2606.26092.md","query":{}}">
TryOnCrafter: Unleashing Camera Trajectories for Realistic Video Virtual Try-on via a Renderable 4D Try-on Proxy
Published on Jun 24
· Submitted by lalala on Jun 25 Authors: ,
,
,
,
,
,
,
,
,
Abstract
Camera-controllable video virtual try-on framework uses a 4D proxy with explicit human-environment decoupling and DiT-based video generation for omnidirectional viewing.
While Video Virtual Try-on (VVT) has achieved remarkable progress in synthesizing realistic garment overlays on dynamic subjects, existing paradigms remains fundamentally constrained by a passive dependency on source camera trajectories, failing to accommodate the requisite interactive freedom for omnidirectional viewpoint exploration. To address this limitation, we define a pioneering research frontier: Camera-controllable Video Virtual Try-on (CaM-VVT). Unlike conventional VVT, CaM-VVT not only necessitates viewpoint-agnostic texture hallucination but also strict structural synchronization between non-rigid human dynamics and background contexts under arbitrary, unconstrained camera movements. To tackle these challenges, we present TryOnCrafter, the first unified DiT-based framework specifically architected for the CaM-VVT task. Departing from implicit pixel-space manipulation, we introduce a Renderable 4D Try-on Proxy that explicitly decouples the human subject from the environment. This is achieved by distilling high-fidelity 2D try-on priors into a clothed 3DGS-based avatar, which is subsequently animated via SMPL-X sequences and metric-aligned into a reconstructed background point cloud. This proxy establishes a robust structural foundation with superior texture density and motion integrity. Our Proxy-Anchored Video DiT leverages this robust structural foundation as a primary geometric anchor, ensuring that the synthesized photorealistic videos are strictly constrained by prescribed trajectories and physically plausible deformations. Benefiting from the inherent editability of the 4D proxy, TryOnCrafter facilitates diverse downstream applications, including human relocalization, ``bullet time'' effects, and 360-degree orbital viewing.
Community
While Video Virtual Try-on (VVT) has achieved remarkable progress in synthesizing realistic garment overlays on dynamic subjects, existing paradigms remains fundamentally constrained by a passive dependency on source camera trajectories, failing to accommodate the requisite interactive freedom for omnidirectional viewpoint exploration. To address this limitation, we define a pioneering research frontier: Camera-controllable Video Virtual Try-on (CaM-VVT). Unlike conventional VVT, CaM-VVT not only necessitates viewpoint-agnostic texture hallucination but also strict structural synchronization between non-rigid human dynamics and background contexts under arbitrary, unconstrained camera movements. To tackle these challenges, we present TryOnCrafter, the first unified DiT-based framework specifically architected for the CaM-VVT task. Departing from implicit pixel-space manipulation, we introduce a Renderable 4D Try-on Proxy that explicitly decouples the human subject from the environment. This is achieved by distilling high-fidelity 2D try-on priors into a clothed 3DGS-based avatar, which is subsequently animated via SMPL-X sequences and metric-aligned into a reconstructed background point cloud. This proxy establishes a robust structural foundation with superior texture density and motion integrity. Our Proxy-Anchored Video DiT leverages this robust structural foundation as a primary geometric anchor, ensuring that the synthesized photorealistic videos are strictly constrained by prescribed trajectories and physically plausible deformations. Benefiting from the inherent editability of the 4D proxy, TryOnCrafter facilitates diverse downstream applications, including human relocalization, ``bullet time'' effects, and 360-degree orbital viewing.
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/2606.26092 in a model README.md to link it from this page.
Cite arxiv.org/abs/2606.26092 in a dataset README.md to link it from this page.
Cite arxiv.org/abs/2606.26092 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.