Browse > Computer Vision > Semantic Segmentation > 3D Part Segmentation

3D Part Segmentation

12 papers with code · Computer Vision

Segmenting 3D object parts

Leaderboards

Greatest papers with code

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

NeurIPS 2017 charlesq34/pointnet2

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

3D PART SEGMENTATION

Submanifold Sparse Convolutional Networks

5 Jun 2017facebookresearch/SparseConvNet

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

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

3D PART SEGMENTATION

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

NeurIPS 2018 yangyanli/PointCNN

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

3D INSTANCE SEGMENTATION 3D PART SEGMENTATION

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.

3D PART SEGMENTATION 3D SHAPE ANALYSIS CUBE ENGRAVING CLASSIFICATION

DeepGCNs: Can GCNs Go as Deep as CNNs?

ICCV 2019 2019 lightaime/deep_gcns

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.

3D PART SEGMENTATION 3D SEMANTIC SEGMENTATION NODE CLASSIFICATION

PointConv: Deep Convolutional Networks on 3D Point Clouds

CVPR 2019 DylanWusee/pointconv

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.

3D PART SEGMENTATION DENSITY ESTIMATION

SPLATNet: Sparse Lattice Networks for Point Cloud Processing

CVPR 2018 NVlabs/splatnet

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.

3D PART SEGMENTATION

Escape from Cells: Deep Kd-Networks for the Recognition of 3D Point Cloud Models

ICCV 2017 fxia22/kdnet.pytorch

We present a new deep learning architecture (called Kd-network) that is designed for 3D model recognition tasks and works with unstructured point clouds.

3D PART SEGMENTATION