Point Cloud Classification

111 papers with code • 2 benchmarks • 2 datasets

Point Cloud Classification is a task involving the classification of unordered 3D point sets (point clouds).

Libraries

Use these libraries to find Point Cloud Classification models and implementations

Most implemented papers

Revisiting Point Cloud Shape Classification with a Simple and Effective Baseline

princeton-vl/SimpleView 9 Jun 2021

It also outperforms state-of-the-art methods on ScanObjectNN, a real-world point cloud benchmark, and demonstrates better cross-dataset generalization.

Dynamic Edge-Conditioned Filters in Convolutional Neural Networks on Graphs

mys007/ecc CVPR 2017

A number of problems can be formulated as prediction on graph-structured data.

Adversarial shape perturbations on 3D point clouds

Daniel-Liu-c0deb0t/Adversarial-point-perturbations-on-3D-objects 16 Aug 2019

The importance of training robust neural network grows as 3D data is increasingly utilized in deep learning for vision tasks in robotics, drone control, and autonomous driving.

Geometric Back-projection Network for Point Cloud Classification

ShiQiu0419/GBNet 28 Nov 2019

As the basic task of point cloud analysis, classification is fundamental but always challenging.

PointHop++: A Lightweight Learning Model on Point Sets for 3D Classification

minzhang-1/PointHop2 9 Feb 2020

The PointHop method was recently proposed by Zhang et al. for 3D point cloud classification with unsupervised feature extraction.

Revisiting Point Cloud Classification with a Simple and Effective Baseline

princeton-vl/SimpleView 1 Jan 2021

It also outperforms state-of-the-art methods on ScanObjectNN, a real-world point cloud benchmark, and demonstrates better cross-dataset generalization.

PointCutMix: Regularization Strategy for Point Cloud Classification

jiachens/ModelNet40-C 5 Jan 2021

As 3D point cloud analysis has received increasing attention, the insufficient scale of point cloud datasets and the weak generalization ability of networks become prominent.

PAConv: Position Adaptive Convolution with Dynamic Kernel Assembling on Point Clouds

CVMI-Lab/PAConv CVPR 2021

The key of PAConv is to construct the convolution kernel by dynamically assembling basic weight matrices stored in Weight Bank, where the coefficients of these weight matrices are self-adaptively learned from point positions through ScoreNet.

Walk in the Cloud: Learning Curves for Point Clouds Shape Analysis

tiangexiang/CurveNet ICCV 2021

Discrete point cloud objects lack sufficient shape descriptors of 3D geometries.

Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modeling

lulutang0608/Point-BERT CVPR 2022

Inspired by BERT, we devise a Masked Point Modeling (MPM) task to pre-train point cloud Transformers.