<a href=\"https://research.nvidia.com/labs/sil/projects/adavomp/\" rel=\"nofollow\">https://research.nvidia.com/labs/sil/projects/adavomp/</a></p>\n<p><video src=\"https://cdn-uploads.huggingface.co/production/uploads/60796959c59d9e1697fa2324/wYojJxDztIO65l_YUR6EK.mp4\" controls=\"\" class=\"max-w-full!\"></video></p>","updatedAt":"2026-06-19T02:21:00.003Z","author":{"_id":"60796959c59d9e1697fa2324","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/60796959c59d9e1697fa2324/wxnDm-p3YgB95NV2p4LGF.png","fullname":"Rishit Dagli","name":"rishitdagli","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":12,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.5912497043609619},"editors":["rishitdagli"],"editorAvatarUrls":["https://cdn-avatars.huggingface.co/v1/production/uploads/60796959c59d9e1697fa2324/wxnDm-p3YgB95NV2p4LGF.png"],"reactions":[],"isReport":false}}],"primaryEmailConfirmed":false,"paper":{"id":"2606.18231","authors":[{"_id":"6a32043ebc818ff14e453d9e","name":"Rishit Dagli","hidden":false},{"_id":"6a32043ebc818ff14e453d9f","name":"Donglai Xiang","hidden":false},{"_id":"6a32043ebc818ff14e453da0","name":"Vismay Modi","hidden":false},{"_id":"6a32043ebc818ff14e453da1","name":"Xuning Yang","hidden":false},{"_id":"6a32043ebc818ff14e453da2","name":"Gavriel State","hidden":false},{"_id":"6a32043ebc818ff14e453da3","name":"David I. W. Levin","hidden":false},{"_id":"6a32043ebc818ff14e453da4","name":"Maria Shugrina","hidden":false}],"publishedAt":"2026-06-16T00:00:00.000Z","submittedOnDailyAt":"2026-06-19T00:00:00.000Z","title":"Adaptive Volumetric Mechanical Property Fields Invariant to Resolution","submittedOnDailyBy":{"_id":"60796959c59d9e1697fa2324","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/60796959c59d9e1697fa2324/wxnDm-p3YgB95NV2p4LGF.png","isPro":false,"fullname":"Rishit Dagli","user":"rishitdagli","type":"user","name":"rishitdagli"},"summary":"Accurate mechanical properties (or materials) Young's modulus (E), Poisson's ratio (ν) and density (ρ) are essential for reliable physics simulation of digital worlds, but most 3D assets lack this information. We propose AdaVoMP, a method for predicting accurate dense spatially-varying (E, ν, ρ) for input 3D objects across representations, improving the resolution, accuracy, and memory efficiency over the state-of-the-art. The foundation of our technique is a sparse and adaptive voxel structure SAV that efficiently represents both the input 3D shape and the material field output. We replace the fixed-voxel model of the most accurate prior method, VoMP, with a novel sparse transformer encoder-decoder model that learns to generate a unique SAV autoregressively for every input shape to represent its materials, achieving a resolution 16^3times higher than prior art. Experiments show that AdaVoMP estimates more accurate volumetric properties, even with lesser test-time compute than all prior art. This allows us to convert high-resolution complex 3D objects into simulation-ready assets, resulting in realistic deformable simulations.","upvotes":2,"discussionId":"6a32043ebc818ff14e453da5","ai_summary":"AdaVoMP predicts dense spatially-varying mechanical properties for 3D objects using a sparse adaptive voxel structure and transformer encoder-decoder model, enabling realistic deformable simulations with improved accuracy and efficiency.","ai_keywords":["voxel structure","sparse transformer encoder-decoder","autoregressive generation","mechanical properties","Young's modulus","Poisson's ratio","density","deformable simulations"],"ai_summary_model":"Qwen/Qwen2.5-Coder-32B-Instruct","organization":{"_id":"60262b67268c201cdc8b7d43","name":"nvidia","fullname":"NVIDIA","avatar":"https://cdn-avatars.huggingface.co/v1/production/uploads/65df9200dc3292a8983e5017/Vs5FPVCH-VZBipV3qKTuy.png"}},"canReadDatabase":false,"canManagePapers":false,"canSubmit":false,"hasHfLevelAccess":false,"upvoted":false,"upvoters":[{"_id":"60796959c59d9e1697fa2324","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/60796959c59d9e1697fa2324/wxnDm-p3YgB95NV2p4LGF.png","isPro":false,"fullname":"Rishit Dagli","user":"rishitdagli","type":"user"},{"_id":"6407e5294edf9f5c4fd32228","avatarUrl":"/avatars/8e2d55460e9fe9c426eb552baf4b2cb0.svg","isPro":false,"fullname":"Stoney Kang","user":"sikang99","type":"user"}],"acceptLanguages":["en"],"dailyPaperRank":0,"organization":{"_id":"60262b67268c201cdc8b7d43","name":"nvidia","fullname":"NVIDIA","avatar":"https://cdn-avatars.huggingface.co/v1/production/uploads/65df9200dc3292a8983e5017/Vs5FPVCH-VZBipV3qKTuy.png"},"markdownContentUrl":"https://huggingface.co/buckets/huggingchat/papers-content/resolve/2606/2606.18231.md","query":{}}">
Adaptive Volumetric Mechanical Property Fields Invariant to Resolution
Abstract
AdaVoMP predicts dense spatially-varying mechanical properties for 3D objects using a sparse adaptive voxel structure and transformer encoder-decoder model, enabling realistic deformable simulations with improved accuracy and efficiency.
Accurate mechanical properties (or materials) Young's modulus (E), Poisson's ratio (ν) and density (ρ) are essential for reliable physics simulation of digital worlds, but most 3D assets lack this information. We propose AdaVoMP, a method for predicting accurate dense spatially-varying (E, ν, ρ) for input 3D objects across representations, improving the resolution, accuracy, and memory efficiency over the state-of-the-art. The foundation of our technique is a sparse and adaptive voxel structure SAV that efficiently represents both the input 3D shape and the material field output. We replace the fixed-voxel model of the most accurate prior method, VoMP, with a novel sparse transformer encoder-decoder model that learns to generate a unique SAV autoregressively for every input shape to represent its materials, achieving a resolution 16^3times higher than prior art. Experiments show that AdaVoMP estimates more accurate volumetric properties, even with lesser test-time compute than all prior art. This allows us to convert high-resolution complex 3D objects into simulation-ready assets, resulting in realistic deformable simulations.
Community
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/2606.18231 in a model README.md to link it from this page.
Cite arxiv.org/abs/2606.18231 in a dataset README.md to link it from this page.
Cite arxiv.org/abs/2606.18231 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.