PMP-Net: Point Cloud Completion by Learning Multi-step Point Moving Paths
Preprint
Abstract
The task of point cloud completion aims to predict the missing part for an incomplete 3D shape. A widely used strategy is to generate a complete point cloud from the incomplete one. However, the unordered nature of point clouds will degrade the generation of high-quality 3D shapes, as the detailed topology and structure of discrete points are hard to be captured by the generative process only using a latent code. In this paper, we address the above problem by reconsidering the completion task from a new perspective, where we formulate the prediction as a point cloud deformation process. Specifically, we design a novel neural network, named PMP-Net, to mimic the behavior of an earth mover. It moves each point of the incomplete input to complete the point cloud, where the total distance of point moving paths (PMP) should be shortest. Therefore, PMP-Net predicts a unique point moving path for each point according to the constraint of total point moving distances. As a result, the network learns a strict and unique correspondence on point-level, which can capture the detailed topology and structure relationships between the incomplete shape and the complete target, and thus improves the quality of the predicted complete shape. We conduct comprehensive experiments on Completion3D and PCN datasets, which demonstrate our advantages over the state-of-the-art point cloud completion methods.Keywords
All Related Versions
This publication has 15 references indexed in Scilit:
- Point Set Voting for Partial Point Cloud AnalysisIEEE Robotics and Automation Letters, 2021
- SoftPoolNet: Shape Descriptor for Point Cloud Completion and Classification2020
- A survey of visual analytics techniques for machine learningComputational Visual Media, 2020
- Detail Preserved Point Cloud Completion via Separated Feature Aggregation2020
- GRNet: Gridding Residual Network for Dense Point Cloud Completion2020
- Reconstructing 3D Shapes From Multiple Sketches Using Direct Shape OptimizationIEEE Transactions on Image Processing, 2020
- Local Frequency Interpretation and Non-Local Self-Similarity on Graph for Point Cloud InpaintingIEEE Transactions on Image Processing, 2019
- 3D2SeqViews: Aggregating Sequential Views for 3D Global Feature Learning by CNN With Hierarchical Attention AggregationIEEE Transactions on Image Processing, 2019
- SeqViews2SeqLabels: Learning 3D Global Features via Aggregating Sequential Views by RNN With AttentionIEEE Transactions on Image Processing, 2018
- The Earth Mover's Distance as a Metric for Image RetrievalInternational Journal of Computer Vision, 2000