Comprehensive Review of Deep Learning-Based 3D Point Cloud Completion Processing and Analysis

TL;DR

This paper provides a comprehensive survey of deep learning methods for 3D point cloud completion, comparing various approaches, datasets, and applications, and discussing future research directions in this rapidly evolving field.

Contribution

It offers an extensive review of existing deep learning techniques for point cloud completion, highlighting their differences, datasets, applications, and potential future trends.

Findings

Deep learning significantly improves point cloud completion quality.

Comparison of point-based, convolution-based, graph-based, and generative approaches.

Identification of key datasets and applications in the field.

Abstract

Point cloud completion is a generation and estimation issue derived from the partial point clouds, which plays a vital role in the applications in 3D computer vision. The progress of deep learning (DL) has impressively improved the capability and robustness of point cloud completion. However, the quality of completed point clouds is still needed to be further enhanced to meet the practical utilization. Therefore, this work aims to conduct a comprehensive survey on various methods, including point-based, convolution-based, graph-based, and generative model-based approaches, etc. And this survey summarizes the comparisons among these methods to provoke further research insights. Besides, this review sums up the commonly used datasets and illustrates the applications of point cloud completion. Eventually, we also discussed possible research trends in this promptly expanding field.