Morphing and Sampling Network for Dense Point Cloud Completion (2019-11-30T00:00:00.000000Z)

TL;DR

This work proposes a novel approach to complete the partial point cloud in two stages, which outperforms the existing methods in both the Earth Mover's Distance (EMD) and the Chamfer Distance (CD).

Abstract

3D point cloud completion, the task of inferring the complete geometric shape from a partial point cloud, has been attracting attention in the community. For acquiring high-fidelity dense point clouds and avoiding uneven distribution, blurred details, or structural loss of existing methods' results, we propose a novel approach to complete the partial point cloud in two stages. Specifically, in the first stage, the approach predicts a complete but coarse-grained point cloud with a collection of parametric surface elements. Then, in the second stage, it merges the coarse-grained prediction with the input point cloud by a novel sampling algorithm. Our method utilizes a joint loss function to guide the distribution of the points. Extensive experiments verify the effectiveness of our method and demonstrate that it outperforms the existing methods in both the Earth Mover's Distance (EMD) and the Chamfer Distance (CD).

Authors

Shimin Hu

8 papers

Jing Shao

8 papers

Minghua Liu

5 papers

TL;DR

Abstract

Authors

References47 items

Semantic Labeling and Instance Segmentation of 3D Point Clouds Using Patch Context Analysis and Multiscale Processing

TopNet: Structural Point Cloud Decoder

RL-GAN-Net: A Reinforcement Learning Agent Controlled GAN Network for Real-Time Point Cloud Shape Completion

Relation-Shape Convolutional Neural Network for Point Cloud Analysis

3DN: 3D Deformation Network

DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation

Learning Implicit Fields for Generative Shape Modeling

PCN: Point Completion Network

High Fidelity Semantic Shape Completion for Point Clouds Using Latent Optimization

PointSIFT: A SIFT-like Network Module for 3D Point Cloud Semantic Segmentation

Tangent Convolutions for Dense Prediction in 3D

Learning 3D Shape Completion Under Weak Supervision

SPLATNet: Sparse Lattice Networks for Point Cloud Processing

A Papier-Mache Approach to Learning 3D Surface Generation

Uniformization and Density Adaptation for Point Cloud Data Via Graph Laplacian

Dynamic Graph CNN for Learning on Point Clouds

PointCNN: Convolution On X-Transformed Points

Mining Point Cloud Local Structures by Kernel Correlation and Graph Pooling

FoldingNet: Point Cloud Auto-Encoder via Deep Grid Deformation

Deformable Shape Completion with Graph Convolutional Autoencoders

Large-Scale Point Cloud Semantic Segmentation with Superpoint Graphs

High-Resolution Shape Completion Using Deep Neural Networks for Global Structure and Local Geometry Inference

Learning Representations and Generative Models for 3D Point Clouds

PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space

Transformation-Grounded Image Generation Network for Novel 3D View Synthesis

PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation

A Point Set Generation Network for 3D Object Reconstruction from a Single Image

Shape Completion Using 3D-Encoder-Predictor CNNs and Shape Synthesis

ShapeNet: An Information-Rich 3D Model Repository

Multi-view 3D Models from Single Images with a Convolutional Network

Data-driven structural priors for shape completion

Convolutional wasserstein distances

Approximate Symmetry Detection in Partial 3D Meshes

Sinkhorn Distances: Lightspeed Computation of Optimal Transport

Structure recovery by part assembly

Parallel Poisson disk sampling

A robust hole-filling algorithm for triangular mesh

Shape from symmetry

Example-based 3D scan completion

Filling holes in complex surfaces using volumetric diffusion

The ball-pivoting algorithm for surface reconstruction

Auction algorithms for network flow problems: A tutorial introduction

Shortest connection networks and some generalizations

and Zhang

and Agrawal

and Simonovsky

and Geiger

Field of Study

Venue Information

Name

Type

URL

Alternate Names