We propose a novel approach for probabilistic generative modeling of 3D shapes. Unlike most existing models that learn to deterministically translate a latent vector to a shape, our model, Point-Voxel Diffusion (PVD), is a unified, probabilistic formulation for unconditional shape generation and conditional, multi-modal shape completion. PVD marries denoising diffusion models with the hybrid, point-voxel representation of 3D shapes. It can be viewed as a series of denoising steps, reversing the diffusion process from observed point cloud data to Gaussian noise, and is trained by optimizing a variational lower bound to the (conditional) likelihood function. Experiments demonstrate that PVD is capable of synthesizing high-fidelity shapes, completing partial point clouds, and generating multiple completion results from single-view depth scans of real objects.
翻译:我们提出一种新的3D形状概率基因模型方法。 与大多数现有模型不同的是,我们的模式,即点-福瑟扩散(PVD),是无条件形状生成和有条件、多式形状完成的统一、概率配方。 PVD将拆分的传播模型与3D形状的混合、点-voxel表示式结合。它可以被视为一系列分解步骤,将观测到的云数据扩散过程从观测到的云层数据转向高斯噪音,并且通过优化与(有条件)可能性功能的更低限制而接受培训。 实验表明,PVD能够将高非性形状合成,完成部分点云,并通过对真实物体的单视深度扫描产生多重完成结果。