# 3D Part Segmentation Edit

14 papers with code · Computer Vision

Segmenting 3D object parts

( Image credit: MeshCNN: A Network with an Edge )

TREND DATASET BEST METHOD PAPER TITLE PAPER CODE COMPARE

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

Point cloud is an important type of geometric data structure.

2,739

# 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.

SOTA for Semantic Segmentation on S3DIS (Accuracy metric )

1,647

# Submanifold Sparse Convolutional Networks

Convolutional network are the de-facto standard for analysing spatio-temporal data such as images, videos, 3D shapes, etc.

#6 best model for 3D Part Segmentation on ShapeNet-Part (Instance Average IoU metric)

1,158

# 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.

SOTA for 3D Instance Segmentation on S3DIS (mIoU metric )

1,035

# MeshCNN: A Network with an Edge

16 Sep 2018ranahanocka/MeshCNN

In this paper, we utilize the unique properties of the mesh for a direct analysis of 3D shapes using MeshCNN, a convolutional neural network designed specifically for triangular meshes.

855

# DeepGCNs: Can GCNs Go as Deep as CNNs?

Finally, we use these new concepts to build a very deep 56-layer GCN, and show how it significantly boosts performance (+3. 7% mIoU over state-of-the-art) in the task of point cloud semantic segmentation.

519

# 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.

365

# SPLATNet: Sparse Lattice Networks for Point Cloud Processing

We present a network architecture for processing point clouds that directly operates on a collection of points represented as a sparse set of samples in a high-dimensional lattice.

249

# 3D Point Capsule Networks

In this paper, we propose 3D point-capsule networks, an auto-encoder designed to process sparse 3D point clouds while preserving spatial arrangements of the input data.

196

# ConvPoint: Continuous Convolutions for Point Cloud Processing

4 Apr 2019aboulch/ConvPoint

Point clouds are unstructured and unordered data, as opposed to images.

111