Adaptive Volumetric Mechanical Property Fields Invariant to Resolution
English summary
The paper proposes AdaVoMP, a method to predict dense spatially-varying mechanical properties (Young's modulus, Poisson's ratio, and density) for input 3D objects across representations. It introduces a sparse adaptive voxel structure (SAV) to efficiently represent shape and material fields, and a novel sparse transformer encoder-decoder that autoregressively generates a unique SAV for each input. AdaVoMP achieves a resolution 16³ times higher than the prior state-of-the-art VoMP, with better accuracy even at lower test-time compute. This allows conversion of high-resolution complex 3D objects into simulation-ready assets for realistic deformable simulations.
Chinese summary
论文提出AdaVoMP，一种为输入3D物体预测密集空间变化的杨氏模量、泊松比和密度的方法。它引入稀疏自适应体素结构（SAV）高效表示形状和材料场，并采用新颖的稀疏Transformer编码器-解码器，为每个输入自回归生成唯一的SAV。AdaVoMP的分辨率比先前最优方法VoMP高出16³倍，且以更低的测试计算量实现了更高精度，支持将高分辨率复杂3D物体转化为可供真实变形模拟的资产。
Key points
Predicts dense spatially-varying Young's modulus, Poisson's ratio, and density for 3D objects.
为3D物体预测密集空间变化的杨氏模量、泊松比和密度。
Uses a sparse adaptive voxel structure (SAV) and a novel sparse transformer encoder-decoder that generates SAV autoregressively per shape.
采用稀疏自适应体素结构（SAV）和稀疏Transformer编码器-解码器，为每个形状自回归生成SAV。
Achieves 16³ times higher resolution than the prior art VoMP.
分辨率达到先前方法VoMP的16³倍。
Outperforms prior methods in accuracy with less test-time compute.
以更低的测试计算量实现比先前方法更高的精度。
Enables conversion of complex high-resolution 3D objects into simulation-ready assets for realistic deformable simulations.
支持将复杂高分辨率3D物体转化为可供真实变形模拟的资产。