Diffusion-Occ: 3D Point Cloud Completion via Occupancy Diffusion
Abstract
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.
Cite
@article{arxiv.2408.14846,
title = {Diffusion-Occ: 3D Point Cloud Completion via Occupancy Diffusion},
author = {Guoqing Zhang and Jian Liu},
journal= {arXiv preprint arXiv:2408.14846},
year = {2024}
}
Comments
After a closer examination of our work, we've determined that our experiments are not thorough and robust enough, possibly impacting the accuracy of our conclusions. Hence, we've decided to withdraw our article and, after refining our experiments, intend to resubmit the paper once significant improvements have been made