分辨率不变的自适应体积力学性能场

摘要

精确的力学属性（或材料参数）——杨氏模量（E）、泊松比（ν）和密度（ρ）——对数字世界的可靠物理仿真至关重要，但大多数三维资产缺乏此类信息。我们提出AdaVoMP方法，用于预测输入三维物体在不同表征形式下的精确密集空间变化参数（E, ν, ρ），相较于现有技术显著提升了分辨率、精度和内存效率。该技术的核心是一种稀疏自适应体素结构（SAV），能够高效同时表征输入三维形状与材料场输出。我们将现有最精确方法VoMP的固定体素模型，替换为新型稀疏Transformer编码器-解码器模型，该模型能够针对每个输入形状自回归地学习生成独特的SAV以表征其材料，实现的分辨率较现有技术高出16³倍。实验表明，即使测试时计算量低于所有现有方法，AdaVoMP仍能估计更精确的体积属性。这使我们能够将高分辨率复杂三维物体转化为可直接用于仿真的资产，从而获得逼真的可变形仿真结果。

English

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.