Point clouds are crucial for capturing three-dimensional data but often suffer from incompleteness due to limitations such as resolution and occlusion. Traditional methods typically rely on point-based approaches within discriminative frameworks for point cloud completion. In this paper, we introduce \textbf{Diffusion-Occ}, a novel framework for Diffusion Point Cloud Completion. Diffusion-Occ utilizes a two-stage coarse-to-fine approach. In the first stage, the Coarse Density Voxel Prediction Network (CDNet) processes partial points to predict coarse density voxels, streamlining global feature extraction through voxel classification, as opposed to previous regression-based methods. In the second stage, we introduce the Occupancy Generation Network (OccGen), a conditional occupancy diffusion model based on a transformer architecture and enhanced by our Point-Voxel Fuse (PVF) block. This block integrates coarse density voxels with partial points to leverage both global and local features for comprehensive completion. By thresholding the occupancy field, we convert it into a complete point cloud. Additionally, our method employs diverse training mixtures and efficient diffusion parameterization to enable effective one-step sampling during both training and inference. Experimental results demonstrate that Diffusion-Occ outperforms existing discriminative and generative methods.

翻译：点云是捕获三维数据的关键，但由于分辨率和遮挡等限制，常常存在不完整的问题。传统方法通常在判别式框架内依赖基于点的方法进行点云补全。本文提出 \textbf{Diffusion-Occ}，一种用于扩散点云补全的新框架。Diffusion-Occ 采用由粗到精的两阶段方法。在第一阶段，粗粒度密度体素预测网络（CDNet）处理部分点以预测粗粒度密度体素，通过体素分类简化全局特征提取，这与先前基于回归的方法不同。在第二阶段，我们引入了占据概率生成网络（OccGen），这是一个基于 Transformer 架构的条件占据概率扩散模型，并通过我们提出的点-体素融合（PVF）模块进行增强。该模块将粗粒度密度体素与部分点云相结合，以利用全局和局部特征进行全面的补全。通过对占据概率场进行阈值化，我们将其转换为完整的点云。此外，我们的方法采用多样化的训练混合策略和高效的扩散参数化，从而在训练和推理过程中实现有效的一步采样。实验结果表明，Diffusion-Occ 的性能优于现有的判别式和生成式方法。