发表机构
Virginia Tech; Meta（弗吉尼亚理工大学; Meta）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对体素超材料生成中合理性与新颖性的权衡，提出REGDIFF框架，通过潜空间调控和引导扩散，在保持几何合理性的同时提升新颖性与多样性，实验显示显著优于基线。
AI 中文摘要
超材料是人工设计的结构，其力学和物理行为主要由几何形状而非组成成分决定。体素表示为超材料几何生成提供了统一格式，因为它可以在单一立方体离散化中表达桁架、壳体和多孔结构等多种类别。然而，基于体素的生成面临一个合理性与新颖性之间的权衡：接近已知几何有助于保持几何规律性，而远离它们则是新颖性所必需的，但可能产生退化几何。为解决这一挑战，我们提出了REGDIFF，一种将体素表示与潜空间调控和引导扩散相结合的生成框架。REGDIFF引入了一种排斥-下沉（RAS）机制来平滑合理几何的潜分布，以及短程排斥（SRR）引导来抑制生成过于接近已知样本，同时保持几何合理性。我们进一步贡献了一个基于体素的基准，涵盖桁架型和壳体型超材料几何，以及一个用于评估几何合理性、新颖性和多样性的评估模块。实验表明，REGDIFF优于基于体素的生成基线，在两个数据集上平均实现了几何合理性+8.9%、新颖性+46.4%和多样性+128.6%的提升。这些结果表明，REGDIFF是下游评估的有力几何候选生成器。我们的代码在此https URL提供。
英文摘要
Metamaterials are artificially engineered structures whose mechanical and physical behaviors are strongly shaped by geometry rather than composition. Voxel representation provides a unified format for metamaterial geometry generation, as it can express diverse classes such as truss, shell, and porous structures within a single cubic discretization. However, voxel-based generation faces a plausibility-novelty trade-off: staying close to known geometries helps preserve geometric regularities, while moving away from them is necessary for novelty but may produce degenerate geometries. To address this challenge, we propose REGDIFF, a generative framework that couples voxel representation with latent space regulation and guided diffusion. REGDIFF introduces a repel-and-sink (RAS) mechanism to smooth the latent distribution of plausible geometries, and short-range repulsion (SRR) guidance to discourage generation overly close to known samples while maintaining geometric plausibility. We further contribute a voxel-based benchmark covering truss- and shell-type metamaterial geometries, together with an evaluation module for geometric plausibility, novelty, and diversity. Experiments show that REGDIFF outperforms voxel-based generative baselines, achieving +8.9% in geometric plausibility, +46.4% in novelty, and +128.6% in diversity on average across two datasets. These results suggest that REGDIFF is a strong geometry candidate generator for downstream evaluation. Our code is provided at https://github.com/wzhan24/ReGDiff.
