Metraipolis › archive › dc_dd5835d23924
ReGDiff: Guided Diffusion in Regulated Latent Space for Exploring Metamaterial Voxel Geometry — arXiv:2609.34231
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.34231
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T21:02:16.125Z
- SHA-256 of the archived text
61fa156f3329ac6ba3c104e4c533c939399991826f987e2604318e5d4caf997e- Stable URL of this page
https://metraipolis.com/documento/dc_dd5835d23924
How to cite
ReGDiff: Guided Diffusion in Regulated Latent Space for Exploring Metamaterial Voxel Geometry — arXiv:2609.34231 — arXiv (en), https://arxiv.org/abs/2609.34231 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_dd5835d23924 (Metraipolis archive dc_dd5835d23924, sha256 61fa156f3329ac6ba3c104e4c533c939399991826f987e2604318e5d4caf997e)
BibTeX
@misc{dcdd5835d23924,
title = {ReGDiff: Guided Diffusion in Regulated Latent Space for Exploring Metamaterial Voxel Geometry — arXiv:2609.34231},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.34231},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_dd5835d23924; sha256 61fa156f3329ac6ba3c104e4c533c939399991826f987e2604318e5d4caf997e},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.34231. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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 this https URL . Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.AI). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2609.34231 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-07T20:29:02.899Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).