الملخص
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.
الكلمات المفتاحية
بيانات النشر
- المجلة
- غير متاح
- وصول مفتوح
- وصول مفتوح أخضر
اقتبس هذه المقالة
APA 7
Zhan, W., Chen, J., Fu, D., & Zhou, D. (2026). ReGDiff: Guided Diffusion in Regulated Latent Space for Exploring Metamaterial Voxel Geometry. https://omanscience.com/ar/articles/regdiff-guided-diffusion-in-regulated-latent-space-for-exploring-metamaterial-voxel-geometry
MLA 9
Zhan, Wangzhi, et al. "ReGDiff: Guided Diffusion in Regulated Latent Space for Exploring Metamaterial Voxel Geometry." https://omanscience.com/ar/articles/regdiff-guided-diffusion-in-regulated-latent-space-for-exploring-metamaterial-voxel-geometry.
شيكاغو (المؤلف–التاريخ)
Zhan, Wangzhi, Jianpeng Chen, Dongqi Fu, and Dawei Zhou. 2026. "ReGDiff: Guided Diffusion in Regulated Latent Space for Exploring Metamaterial Voxel Geometry." https://omanscience.com/ar/articles/regdiff-guided-diffusion-in-regulated-latent-space-for-exploring-metamaterial-voxel-geometry.
هارفارد
Zhan, W., Chen, J., Fu, D. and Zhou, D. (2026) 'ReGDiff: Guided Diffusion in Regulated Latent Space for Exploring Metamaterial Voxel Geometry', Available at: https://omanscience.com/ar/articles/regdiff-guided-diffusion-in-regulated-latent-space-for-exploring-metamaterial-voxel-geometry.
فانكوفر
Zhan W, Chen J, Fu D, Zhou D. ReGDiff: Guided Diffusion in Regulated Latent Space for Exploring Metamaterial Voxel Geometry. https://omanscience.com/ar/articles/regdiff-guided-diffusion-in-regulated-latent-space-for-exploring-metamaterial-voxel-geometry
IEEE
W. Zhan, J. Chen, D. Fu, and D. Zhou, "ReGDiff: Guided Diffusion in Regulated Latent Space for Exploring Metamaterial Voxel Geometry," https://omanscience.com/ar/articles/regdiff-guided-diffusion-in-regulated-latent-space-for-exploring-metamaterial-voxel-geometry.