Part-aware Shape Generation with Latent 3D Diffusion of Neural Voxel Fields

arXiv:2405.00998v1 Announce Type: new
Abstract: This paper presents a novel latent 3D diffusion model for the generation of neural voxel fields, aiming to achieve accurate part-aware structures. Compared to existing methods, there are two key designs to ensure high-quality and accurate part-aware generation. On one hand, we introduce a latent 3D diffusion process for neural voxel fields, enabling generation at significantly higher resolutions that can accurately capture rich textural and geometric details. On the other hand, a part-aware shape decoder …

abstract arxiv cs.cv designs diffusion diffusion model fields key novel paper part quality type voxel