Spice-E : Structural Priors in 3D Diffusion using Cross-Entity Attention

arXiv:2311.17834v3 Announce Type: replace
Abstract: We are witnessing rapid progress in automatically generating and manipulating 3D assets due to the availability of pretrained text-image diffusion models. However, time-consuming optimization procedures are required for synthesizing each sample, hindering their potential for democratizing 3D content creation. Conversely, 3D diffusion models now train on million-scale 3D datasets, yielding high-quality text-conditional 3D samples within seconds. In this work, we present Spice-E - a neural network that adds structural guidance to 3D diffusion models, extending …

abstract arxiv attention availability cs.cv cs.gr diffusion diffusion models however image image diffusion optimization progress sample text text-image train type