PU-GAN: A Point Cloud Upsampling Adversarial Network (2019-07-25T00:00:00.000000Z)

TL;DR

A new point cloud upsampling network called PU-GAN, which is formulated based on a generative adversarial network (GAN), to learn a rich variety of point distributions from the latent space and upsample points over patches on object surfaces.

Abstract

Point clouds acquired from range scans are often sparse, noisy, and non-uniform. This paper presents a new point cloud upsampling network called PU-GAN, which is formulated based on a generative adversarial network (GAN), to learn a rich variety of point distributions from the latent space and upsample points over patches on object surfaces. To realize a working GAN network, we construct an up-down-up expansion unit in the generator for upsampling point features with error feedback and self-correction, and formulate a self-attention unit to enhance the feature integration. Further, we design a compound loss with adversarial, uniform and reconstruction terms, to encourage the discriminator to learn more latent patterns and enhance the output point distribution uniformity. Qualitative and quantitative evaluations demonstrate the quality of our results over the state-of-the-arts in terms of distribution uniformity, proximity-to-surface, and 3D reconstruction quality.

Authors

P. Heng

25 papers

Chi-Wing Fu

13 papers

D. Cohen-Or

22 papers

TL;DR

Abstract

Authors

References46 items

PointWeb: Enhancing Local Neighborhood Features for Point Cloud Processing

Patch-Based Progressive 3D Point Set Upsampling

PCN: Point Completion Network

EC-Net: an Edge-aware Point set Consolidation Network

High Fidelity Semantic Shape Completion for Point Clouds Using Latent Optimization

Self-Attention Generative Adversarial Networks

SpiderCNN: Deep Learning on Point Sets with Parameterized Convolutional Filters

SPLATNet: Sparse Lattice Networks for Point Cloud Processing

Dynamic Graph CNN for Learning on Point Clouds

PointCNN: Convolution On X-Transformed Points

PU-Net: Point Cloud Upsampling Network

FoldingNet: Point Cloud Auto-Encoder via Deep Grid Deformation

Mining Point Cloud Local Structures by Kernel Correlation and Graph Pooling

Pointwise Convolutional Neural Networks

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

StackGAN++: Realistic Image Synthesis with Stacked Generative Adversarial Networks

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

Improved Adversarial Systems for 3D Object Generation and Reconstruction

Learning Representations and Generative Models for 3D Point Clouds

GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium

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

Weakly Supervised 3D Reconstruction with Adversarial Constraint

ScanNet: Richly-Annotated 3D Reconstructions of Indoor Scenes

StackGAN: Text to Photo-Realistic Image Synthesis with Stacked Generative Adversarial Networks

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

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

Image-to-Image Translation with Conditional Adversarial Networks

Least Squares Generative Adversarial Networks

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

Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network

Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks

Deep points consolidation

SUN RGB-D: A RGB-D scene understanding benchmark suite

Adam: A Method for Stochastic Optimization

On distinguishability criteria for estimating generative models

3d Object Reconstruction from a Single Image.

3D ShapeNets: A deep representation for volumetric shapes

Vision meets robotics: The KITTI dataset

Screened poisson surface reconstruction

A benchmark for surface reconstruction

Edge-aware point set resampling

Consolidation of unorganized point clouds for surface reconstruction

Parameterization-free projection for geometry reconstruction

Deep Learning on Point Sets for 3 D Classification and Segmentation

Computing and Rendering Point Set Surfaces

Ieee Transactions on Visualization and Computer Graphics 1 Efficient and Flexible Sampling with Blue Noise Properties of Triangular Meshes

Field of Study

Journal Information

Name

Page

Venue Information

Name

Type

URL

Alternate Names