Adaptive Volumetric Mechanical Property Fields Invariant to Resolution

Hugging Face Daily Papers Papers

Summary

AdaVoMP uses a sparse adaptive voxel structure and transformer encoder-decoder to predict spatially-varying mechanical properties for 3D objects, enabling high-resolution 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.
Original Article
View Cached Full Text

Cached at: 06/20/26, 02:29 PM

Paper page - Adaptive Volumetric Mechanical Property Fields Invariant to Resolution

Source: https://huggingface.co/papers/2606.18231

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.

Accuratemechanical properties(or materials)Young’s modulus(E),Poisson’s ratio(ν) anddensity(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 adaptivevoxel structureSAV 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 novelsparse transformer encoder-decodermodel 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 realisticdeformable simulations.

View arXiv pageView PDFAdd to collection

Get this paper in your agent:

hf papers read 2606\.18231

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2606.18231 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2606.18231 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2606.18231 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.

Similar Articles

AdaCodec: A Predictive Visual Code for Video MLLMs

Hugging Face Daily Papers

AdaCodec reduces video encoding redundancy in multimodal LLMs by transmitting full visual tokens only when scene prediction fails, otherwise using compact inter-frame change descriptions. It outperforms per-frame RGB baselines at matched token budgets and achieves better or comparable results with significantly fewer tokens, reducing time-to-first-token from 9.26s to 1.62s.