PCDM: Point Cloud Completion by Conditional Diffusion ModelPCDM: Point Cloud Completion by Conditional...C. Zhang et al.

被引：0

作者：

Cheng Zhang ^{[1
]}

Zhiqiang Qi ^{[1
]}

Wenwen Yuan ^{[2
]}

Wanlong Qi ^{[3
]}

Zhengzheng Yang ^{[1
]}

Zhaobing Su ^{[1
]}

机构：

[1] Northwest Institute of Mechanical & Electrical Engineering,Basic Department

[2] National University of Defense Technology,College of Intelligence Science and Technology

[3] Byd Auto Industry Company Limited,Automotive Engineering Research Institute

来源：

Neural Processing Letters | / 57卷 / 3期

关键词：

Deep learning; Computer vision; Point cloud completion; Diffusion model;

D O I：

10.1007/s11063-025-11767-5

中图分类号：

学科分类号：

摘要：

During the point clouds collection process, the errors can be easily introduced into dataset, leading to biases in subsequent analyses, so the completion of point clouds is a critical step of point cloud analysis. In this paper, we introduce a conditional diffusion model architecture (PCDM) to solve point cloud completion problem. The diffusion model has shown remarkable success in image generation and has recently started to be applied in other domains, showing amazing results. By harnessing the potent generative abilities of diffusion models, we progressively get the complete point clouds derived from pure noise data. In the denosing process, we employ a Local-Global Net (LoGNet) to fuse global and local features, guiding the generation of point clouds by the model. Furthermore, to strike a balance between the completeness of the generated point cloud data and local details, we introduce an offset-attention mechanism to extract features from incomplete point clouds. Experiments conducted on multiple public datasets demonstrate that the point cloud completion method proposed in this paper outperforms previous approaches.

引用