# 3D Point Cloud Classification

58 papers with code • 3 benchmarks • 3 datasets

Image: Qi et al

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

Point cloud is an important type of geometric data structure.

3,484

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

By exploiting metric space distances, our network is able to learn local features with increasing contextual scales.

2,176

# PointCNN: Convolution On X-Transformed Points

We present a simple and general framework for feature learning from point cloud.

Ranked #7 on Semantic Segmentation on S3DIS Area5 (oAcc metric)

1,189

# PointCNN: Convolution On $\mathcal{X}$-Transformed Points

The proposed method is a generalization of typical CNNs to feature learning from point clouds, thus we call it PointCNN.

Ranked #1 on 3D Instance Segmentation on S3DIS (mIoU metric)

1,189

# Dynamic Graph CNN for Learning on Point Clouds

24 Jan 2018

Point clouds provide a flexible geometric representation suitable for countless applications in computer graphics; they also comprise the raw output of most 3D data acquisition devices.

1,043

# Perceiver: General Perception with Iterative Attention

4 Mar 2021

The perception models used in deep learning on the other hand are designed for individual modalities, often relying on domain-specific assumptions such as the local grid structures exploited by virtually all existing vision models.

661

# KPConv: Flexible and Deformable Convolution for Point Clouds

Furthermore, these locations are continuous in space and can be learned by the network.

492

# Dynamic Edge-Conditioned Filters in Convolutional Neural Networks on Graphs

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

443

# PCT: Point cloud transformer

17 Dec 2020

It is inherently permutation invariant for processing a sequence of points, making it well-suited for point cloud learning.

Ranked #10 on 3D Part Segmentation on ShapeNet-Part (Instance Average IoU metric)

435

# PointConv: Deep Convolutional Networks on 3D Point Clouds

Besides, our experiments converting CIFAR-10 into a point cloud showed that networks built on PointConv can match the performance of convolutional networks in 2D images of a similar structure.

427