AI RESEARCH
Fast 3D Diffusion for Scalable Granular Media Synthesis
arXiv CS.LG
•
ArXi:2508.19752v2 Announce Type: replace Discrete Element Method (DEM) simulations of granular media are computationally intensive, particularly during initialization phases dominated by large displacements and kinetic energy. This paper presents a novel generative pipeline based on 3D diffusion models that directly synthesizes arbitrarily large granular assemblies in mechanically realistic configurations. The approach employs a two-stage pipeline.