PMP-Net++: Point Cloud Completion by Transformer-Enhanced Multi-step Point Moving Paths

02/19/2022
by   Peng Xiang, et al.
0

Point cloud completion concerns to predict missing part for incomplete 3D shapes. A common strategy is to generate complete shape according to incomplete input. However, unordered nature of point clouds will degrade generation of high-quality 3D shapes, as detailed topology and structure of unordered points are hard to be captured during the generative process using an extracted latent code. We address this problem by formulating completion as point cloud deformation process. Specifically, we design a novel neural network, named PMP-Net++, to mimic behavior of an earth mover. It moves each point of incomplete input to obtain a complete point cloud, where total distance of point moving paths (PMPs) should be the shortest. Therefore, PMP-Net++ predicts unique PMP for each point according to constraint of point moving distances. The network learns a strict and unique correspondence on point-level, and thus improves quality of predicted complete shape. Moreover, since moving points heavily relies on per-point features learned by network, we further introduce a transformer-enhanced representation learning network, which significantly improves completion performance of PMP-Net++. We conduct comprehensive experiments in shape completion, and further explore application on point cloud up-sampling, which demonstrate non-trivial improvement of PMP-Net++ over state-of-the-art point cloud completion/up-sampling methods.

READ FULL TEXT

page 4

page 8

page 9

page 10

page 15

page 16

research
12/07/2020

PMP-Net: Point Cloud Completion by Learning Multi-step Point Moving Paths

The task of point cloud completion aims to predict the missing part for ...
research
11/27/2018

Iterative Transformer Network for 3D Point Cloud

3D point cloud is an efficient and flexible representation of 3D structu...
research
03/04/2023

Improving the quality of dental crown using a Transformer-based method

Designing a synthetic crown is a time-consuming, inconsistent, and labor...
research
11/23/2021

MFM-Net: Unpaired Shape Completion Network with Multi-stage Feature Matching

Unpaired 3D object completion aims to predict a complete 3D shape from a...
research
03/14/2021

Cycle4Completion: Unpaired Point Cloud Completion using Cycle Transformation with Missing Region Coding

In this paper, we present a novel unpaired point cloud completion networ...
research
02/18/2022

Snowflake Point Deconvolution for Point Cloud Completion and Generation with Skip-Transformer

Most existing point cloud completion methods suffered from discrete natu...
research
12/25/2022

Neural Shape Compiler: A Unified Framework for Transforming between Text, Point Cloud, and Program

3D shapes have complementary abstractions from low-level geometry to par...

Please sign up or login with your details

Forgot password? Click here to reset