Point Cloud Super Resolution

7 papers with code • 1 benchmarks • 1 datasets

Point cloud super-resolution is a fundamental problem for 3D reconstruction and 3D data understanding. It takes a low-resolution (LR) point cloud as input and generates a high-resolution (HR) point cloud with rich details

Datasets


Most implemented papers

PU-Net: Point Cloud Upsampling Network

yulequan/PU-Net CVPR 2018

Learning and analyzing 3D point clouds with deep networks is challenging due to the sparseness and irregularity of the data.

Patch-based Progressive 3D Point Set Upsampling

yifita/3PU_pytorch CVPR 2019

We present a detail-driven deep neural network for point set upsampling.

PU-GAN: a Point Cloud Upsampling Adversarial Network

liruihui/PU-GAN ICCV 2019

Point clouds acquired from range scans are often sparse, noisy, and non-uniform.

007: Democratically Finding The Cause of Packet Drops

behnazak/Vigil-007SourceCode 20 Feb 2018

Network failures continue to plague datacenter operators as their symptoms may not have direct correlation with where or why they occur.

PU-GCN: Point Cloud Upsampling using Graph Convolutional Networks

guochengqian/PU-GCN CVPR 2021

We combine Inception DenseGCN with NodeShuffle into a new point upsampling pipeline called PU-GCN.

PUGeo-Net: A Geometry-centric Network for 3D Point Cloud Upsampling

ninaqy/PUGeo ECCV 2020

Matrix $\mathbf T$ approximates the augmented Jacobian matrix of a local parameterization and builds a one-to-one correspondence between the 2D parametric domain and the 3D tangent plane so that we can lift the adaptively distributed 2D samples (which are also learned from data) to 3D space.

Meta-PU: An Arbitrary-Scale Upsampling Network for Point Cloud

pleaseconnectwifi/Meta-PU 9 Feb 2021

Thus, Meta-PU even outperforms the existing methods trained for a specific scale factor only.