About

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

Benchmarks

TREND DATASET BEST METHOD PAPER TITLE PAPER CODE COMPARE

Greatest papers with code

PU-Net: Point Cloud Upsampling Network

CVPR 2018 yulequan/PU-Net

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

POINT CLOUD SUPER RESOLUTION

PU-GAN: a Point Cloud Upsampling Adversarial Network

ICCV 2019 liruihui/PU-GAN

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

3D RECONSTRUCTION POINT CLOUD SUPER RESOLUTION

PU-GCN: Point Cloud Upsampling using Graph Convolutional Networks

30 Nov 2019guochengqian/PU-GCN

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

3D RECONSTRUCTION POINT CLOUD SUPER RESOLUTION

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

ECCV 2020 ninaqy/PUGeo

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.

POINT CLOUD SUPER RESOLUTION

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

9 Feb 2021pleaseconnectwifi/Meta-PU

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

POINT CLOUD SUPER RESOLUTION