PF-Net: Point Fractal Network for 3D Point Cloud Completion (2020-03-01T00:00:00.000000Z)

TL;DR

A Point Fractal Network (PF-Net), a novel learning-based approach for precise and high-fidelity point cloud completion that preserves the spatial arrangements of the incomplete point cloud and can figure out the detailed geometrical structure of the missing region(s) in the prediction.

Abstract

In this paper, we propose a Point Fractal Network (PF-Net), a novel learning-based approach for precise and high-fidelity point cloud completion. Unlike existing point cloud completion networks, which generate the overall shape of the point cloud from the incomplete point cloud and always change existing points and encounter noise and geometrical loss, PF-Net preserves the spatial arrangements of the incomplete point cloud and can figure out the detailed geometrical structure of the missing region(s) in the prediction. To succeed at this task, PF-Net estimates the missing point cloud hierarchically by utilizing a feature-points-based multi-scale generating network. Further, we add up multi-stage completion loss and adversarial loss to generate more realistic missing region(s). The adversarial loss can better tackle multiple modes in the prediction. Our experiments demonstrate the effectiveness of our method for several challenging point cloud completion tasks.

Authors

Feng Ni

2 papers

Zitian Huang

1 papers

Yikuan Yu

1 papers

TL;DR

Abstract

Authors

References43 items

Point Encoder GAN: A deep learning model for 3D point cloud inpainting

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

Libra R-CNN: Towards Balanced Learning for Object Detection

FCOS: Fully Convolutional One-Stage Object Detection

Hybrid Task Cascade for Instance Segmentation

Panoptic Feature Pyramid Networks

3D Point Capsule Networks

Point Cloud GAN

Hypergraph Neural Networks

PCN: Point Completion Network

Multiresolution Tree Networks for 3D Point Cloud Processing

Multi-view Harmonized Bilinear Network for 3D Object Recognition

Triplet-Center Loss for Multi-view 3D Object Retrieval

CapsuleGAN: Generative Adversarial Capsule Network

An Optimization View on Dynamic Routing Between Capsules

PU-Net: Point Cloud Upsampling Network

FoldingNet: Point Cloud Auto-Encoder via Deep Grid Deformation

Cascade R-CNN: Delving Into High Quality Object Detection

VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection

Shape Inpainting Using 3D Generative Adversarial Network and Recurrent Convolutional Networks

A Novel SDASS Descriptor for Fully Encoding the Information of 3D Local Surface

Dynamic Routing Between Capsules

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

A point sampling algorithm for 3D matching of irregular geometries

3D Object Reconstruction from a Single Depth View with Adversarial Learning

Learning Representations and Generative Models for 3D Point Clouds

Learning Efficient Point Cloud Generation for Dense 3D Object Reconstruction

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

Feature Pyramid Networks for Object Detection

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

A scalable active framework for region annotation in 3D shape collections

Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling

Data‐Driven Bending Elasticity Design by Shell Thickness

Context Encoders: Feature Learning by Inpainting

RotationNet: Joint Object Categorization and Pose Estimation Using Multiviews from Unsupervised Viewpoints

Perceptual models of preference in 3D printing direction

3D ShapeNets: A deep representation for volumetric shapes

Relation-Shape Convolutional Neural Network for Point Cloud Analysis

GENERATIVE ADVERSARIAL NETS

Learning representations and generative models for 3 D point clouds A point sampling algorithm for 3 D matching of irregular geometries

Field of Study

Journal Information

Name

Page

Venue Information

Name

Type

URL

Alternate Names