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.

3,197

# 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.

1,965

# Large-Scale 3D Shape Reconstruction and Segmentation from ShapeNet Core55

We introduce a large-scale 3D shape understanding benchmark using data and annotation from ShapeNet 3D object database.

1,403

# Submanifold Sparse Convolutional Networks

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

Ranked #18 on 3D Part Segmentation on ShapeNet-Part (Instance Average IoU metric)

1,403

# PointCNN: Convolution On X-Transformed Points

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

1,137

# 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)

1,137

# 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.

1,057

# Dynamic Graph CNN for Learning on Point Clouds

24 Jan 2018WangYueFt/dgcnn

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.

910

# KPConv: Flexible and Deformable Convolution for Point Clouds

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

Ranked #1 on Scene Segmentation on ScanNet (3DIoU metric)

448

# 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.

405