Segmenting 3D object parts
|Trend||Dataset||Best Method||Paper title||Paper||Code||Compare|
Point cloud is an important type of geometric data structure.
#2 best model for Scene Segmentation on ScanNet
By exploiting metric space distances, our network is able to learn local features with increasing contextual scales.
#2 best model for Semantic Segmentation on ShapeNet
Convolutional network are the de-facto standard for analysing spatio-temporal data such as images, videos, 3D shapes, etc.
SOTA for 3D Part Segmentation on ShapeNet-Part (Instance Average IoU metric )
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.
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.
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.
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.
#3 best model for 3D Part Segmentation on ShapeNet-Part
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.
We present a new deep learning architecture (called Kd-network) that is designed for 3D model recognition tasks and works with unstructured point clouds.
#6 best model for 3D Part Segmentation on ShapeNet-Part
Deep neural networks have enjoyed remarkable success for various vision tasks, however it remains challenging to apply CNNs to domains lacking a regular underlying structures such as 3D point clouds.
#2 best model for 3D Part Segmentation on ShapeNet-Part