Simulation-ready physical 3D assets have emerged as a promising direction owing to their broad applicability in downstream tasks. However, most existing 3D generation methods either neglect physical properties or are limited to a single asset category, e.g., rigid, deformable, or articulated objects. To address these limitations, we introduce PhysX-Omni, a unified framework for simulation-ready physical 3D generation across diverse asset types. Specifically, we develop a novel and efficient geometry representation tailored for Vision-Language Models, which directly encodes high-resolution 3D structures without compression, significantly improving generation performance. In addition, we construct the first general simulation-ready 3D dataset, PhysXVerse, covering diverse indoor and outdoor categories. Furthermore, to comprehensively and flexibly evaluate both generative and understanding capabilities in the wild, we propose PhysX-Bench, which encompasses six key attributes: geometry, absolute scale, material, affordance, kinematics, and function description. Extensive experiments with conventional metrics and PhysX-Bench show that PhysX-Omni performs strongly in both generation and understanding. Moreover, additional studies further validate the potential of PhysX-Omni for applications in simulation-ready scene generation and robotic policy learning. We believe PhysX-Omni can significantly advance a wide range of downstream applications, particularly in embodied AI and physics-based simulation.</p>\n","updatedAt":"2026-05-22T04:03:41.663Z","author":{"_id":"60efe7fa0d920bc7805cada5","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/60efe7fa0d920bc7805cada5/2LBrJBjSCOP5ilZIpWLHl.png","fullname":"Ziqi Huang","name":"Ziqi","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":20,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.8939976096153259},"editors":["Ziqi"],"editorAvatarUrls":["https://cdn-avatars.huggingface.co/v1/production/uploads/60efe7fa0d920bc7805cada5/2LBrJBjSCOP5ilZIpWLHl.png"],"reactions":[],"isReport":false}}],"primaryEmailConfirmed":false,"paper":{"id":"2605.21572","authors":[{"_id":"6a0fd47da53a61ce2e422d2d","name":"Ziang Cao","hidden":false},{"_id":"6a0fd47da53a61ce2e422d2e","name":"Yinghao Liu","hidden":false},{"_id":"6a0fd47da53a61ce2e422d2f","name":"Haitian Li","hidden":false},{"_id":"6a0fd47da53a61ce2e422d30","name":"Runmao Yao","hidden":false},{"_id":"6a0fd47da53a61ce2e422d31","name":"Fangzhou Hong","hidden":false},{"_id":"6a0fd47da53a61ce2e422d32","name":"Zhaoxi Chen","hidden":false},{"_id":"6a0fd47da53a61ce2e422d33","name":"Liang Pan","hidden":false},{"_id":"6a0fd47da53a61ce2e422d34","name":"Ziwei Liu","hidden":false}],"mediaUrls":["https://cdn-uploads.huggingface.co/production/uploads/60efe7fa0d920bc7805cada5/DHGaihMSL3qOlc14orpmf.mp4"],"publishedAt":"2026-05-20T00:00:00.000Z","submittedOnDailyAt":"2026-05-22T00:00:00.000Z","title":"PhysX-Omni: Unified Simulation-Ready Physical 3D Generation for Rigid, Deformable, and Articulated Objects","submittedOnDailyBy":{"_id":"60efe7fa0d920bc7805cada5","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/60efe7fa0d920bc7805cada5/2LBrJBjSCOP5ilZIpWLHl.png","isPro":false,"fullname":"Ziqi Huang","user":"Ziqi","type":"user","name":"Ziqi"},"summary":"Simulation-ready physical 3D assets have emerged as a promising direction owing to their broad applicability in downstream tasks. However, most existing 3D generation methods either neglect physical properties or are limited to a single asset category, e.g., rigid, deformable, or articulated objects. To address these limitations, we introduce PhysX-Omni, a unified framework for simulation-ready physical 3D generation across diverse asset types. Specifically, we develop a novel and efficient geometry representation tailored for Vision-Language Models, which directly encodes high-resolution 3D structures without compression, significantly improving generation performance. In addition, we construct the first general simulation-ready 3D dataset, PhysXVerse, covering diverse indoor and outdoor categories. Furthermore, to comprehensively and flexibly evaluate both generative and understanding capabilities in the wild, we propose PhysX-Bench, which encompasses six key attributes: geometry, absolute scale, material, affordance, kinematics, and function description. Extensive experiments with conventional metrics and PhysX-Bench show that PhysX-Omni performs strongly in both generation and understanding. Moreover, additional studies further validate the potential of PhysX-Omni for applications in simulation-ready scene generation and robotic policy learning. We believe PhysX-Omni can significantly advance a wide range of downstream applications, particularly in embodied AI and physics-based simulation.","upvotes":33,"discussionId":"6a0fd47da53a61ce2e422d35","projectPage":"https://physx-omni.github.io","githubRepo":"https://github.com/physx-omni/PhysX-Omni","githubRepoAddedBy":"user","ai_summary":"PhysX-Omni presents a unified framework for generating simulation-ready 3D assets with physical properties across multiple categories using a novel geometry representation and evaluation benchmarks.","ai_keywords":["3D generation","Vision-Language Models","geometry representation","PhysXVerse dataset","PhysX-Bench","embodied AI","physics-based simulation"],"githubStars":6},"canReadDatabase":false,"canManagePapers":false,"canSubmit":false,"hasHfLevelAccess":false,"upvoted":false,"upvoters":[{"_id":"62ab1ac1d48b4d8b048a3473","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1656826685333-62ab1ac1d48b4d8b048a3473.png","isPro":false,"fullname":"Ziwei Liu","user":"liuziwei7","type":"user"},{"_id":"69b116c65a198623dcbcc950","avatarUrl":"/avatars/18f02ec3df55a8cdaf6f11f854b2589b.svg","isPro":false,"fullname":"Ropedia","user":"Ropedia","type":"user"},{"_id":"69aad2d19b26bfd362137abf","avatarUrl":"/avatars/317807637ce0c185b34be55a4e9ec07e.svg","isPro":false,"fullname":"PhysX-Omni","user":"PhysX-Omni","type":"user"},{"_id":"6736f5a5bdc354756a41c9ab","avatarUrl":"/avatars/214186086384067851c478876b1ef0c2.svg","isPro":false,"fullname":"cao ang","user":"angcao","type":"user"},{"_id":"65af6f6b52e1b2aae437af2e","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/65af6f6b52e1b2aae437af2e/sFC98zLL_ZPS9fvZFi01W.jpeg","isPro":false,"fullname":"Ziang Cao","user":"Caoza","type":"user"},{"_id":"652d06833b5997ed71ce5c46","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/652d06833b5997ed71ce5c46/O_D6bpa5mGxLA7uCjmVCG.jpeg","isPro":false,"fullname":"Zhongang Cai","user":"caizhongang","type":"user"},{"_id":"60efe7fa0d920bc7805cada5","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/60efe7fa0d920bc7805cada5/2LBrJBjSCOP5ilZIpWLHl.png","isPro":false,"fullname":"Ziqi Huang","user":"Ziqi","type":"user"},{"_id":"66aa94cbd59743aa4a65646f","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/66aa94cbd59743aa4a65646f/Z6BKgT_oYcfJgGHQNm9K3.png","isPro":false,"fullname":"Runmao Yao","user":"yaorunmao","type":"user"},{"_id":"64749a0d5aba8edfb2eeaba7","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/64749a0d5aba8edfb2eeaba7/Tiy4DEdp3KQYh7Ij8Vmkn.png","isPro":true,"fullname":"Mutian Xu","user":"Minoday","type":"user"},{"_id":"64f7f5b54101c731ca84ae05","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/64f7f5b54101c731ca84ae05/13DwdxOo3tWbxKDLd44B9.jpeg","isPro":false,"fullname":"Shuai Liu","user":"Choiszt","type":"user"},{"_id":"64b4eecf2fc8324fcb63b404","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/64b4eecf2fc8324fcb63b404/zGYqYVB4-o-GBMybJ8CDA.png","isPro":false,"fullname":"Yunhan Yang","user":"yhyang-myron","type":"user"},{"_id":"69fae2f570585ad496262741","avatarUrl":"/avatars/f4c0b4a39cf28f35ad1b030248ee6fdc.svg","isPro":false,"fullname":"AnonymousSubmitt","user":"AnonymousSubmitt","type":"user"}],"acceptLanguages":["en"],"dailyPaperRank":0,"markdownContentUrl":"https://huggingface.co/buckets/huggingchat/papers-content/resolve/2605/2605.21572.md"}">
PhysX-Omni: Unified Simulation-Ready Physical 3D Generation for Rigid, Deformable, and Articulated Objects
Abstract
PhysX-Omni presents a unified framework for generating simulation-ready 3D assets with physical properties across multiple categories using a novel geometry representation and evaluation benchmarks.
AI-generated summary
Simulation-ready physical 3D assets have emerged as a promising direction owing to their broad applicability in downstream tasks. However, most existing 3D generation methods either neglect physical properties or are limited to a single asset category, e.g., rigid, deformable, or articulated objects. To address these limitations, we introduce PhysX-Omni, a unified framework for simulation-ready physical 3D generation across diverse asset types. Specifically, we develop a novel and efficient geometry representation tailored for Vision-Language Models, which directly encodes high-resolution 3D structures without compression, significantly improving generation performance. In addition, we construct the first general simulation-ready 3D dataset, PhysXVerse, covering diverse indoor and outdoor categories. Furthermore, to comprehensively and flexibly evaluate both generative and understanding capabilities in the wild, we propose PhysX-Bench, which encompasses six key attributes: geometry, absolute scale, material, affordance, kinematics, and function description. Extensive experiments with conventional metrics and PhysX-Bench show that PhysX-Omni performs strongly in both generation and understanding. Moreover, additional studies further validate the potential of PhysX-Omni for applications in simulation-ready scene generation and robotic policy learning. We believe PhysX-Omni can significantly advance a wide range of downstream applications, particularly in embodied AI and physics-based simulation.
Community
Simulation-ready physical 3D assets have emerged as a promising direction owing to their broad applicability in downstream tasks. However, most existing 3D generation methods either neglect physical properties or are limited to a single asset category, e.g., rigid, deformable, or articulated objects. To address these limitations, we introduce PhysX-Omni, a unified framework for simulation-ready physical 3D generation across diverse asset types. Specifically, we develop a novel and efficient geometry representation tailored for Vision-Language Models, which directly encodes high-resolution 3D structures without compression, significantly improving generation performance. In addition, we construct the first general simulation-ready 3D dataset, PhysXVerse, covering diverse indoor and outdoor categories. Furthermore, to comprehensively and flexibly evaluate both generative and understanding capabilities in the wild, we propose PhysX-Bench, which encompasses six key attributes: geometry, absolute scale, material, affordance, kinematics, and function description. Extensive experiments with conventional metrics and PhysX-Bench show that PhysX-Omni performs strongly in both generation and understanding. Moreover, additional studies further validate the potential of PhysX-Omni for applications in simulation-ready scene generation and robotic policy learning. We believe PhysX-Omni can significantly advance a wide range of downstream applications, particularly in embodied AI and physics-based simulation.
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/2605.21572 in a model README.md to link it from this page.
Cite arxiv.org/abs/2605.21572 in a dataset README.md to link it from this page.
Cite arxiv.org/abs/2605.21572 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.