3D Part Segmentation
69 papers with code • 2 benchmarks • 6 datasets
Segmenting 3D object parts
( Image credit: MeshCNN: A Network with an Edge )
Libraries
Use these libraries to find 3D Part Segmentation models and implementations
ShapeNet
IntrA
LiDAR-MOS
Teeth3DS+
Workshop Tools Dataset
TomoSAM
Most implemented papers
PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space
yanx27/Pointnet_Pointnet2_pytorch
•
•
NeurIPS 2017
By exploiting metric space distances, our network is able to learn local features with increasing contextual scales.
Point Transformer
Pointcept/Pointcept
•
•
ICCV 2021
For example, on the challenging S3DIS dataset for large-scale semantic scene segmentation, the Point Transformer attains an mIoU of 70. 4% on Area 5, outperforming the strongest prior model by 3. 3 absolute percentage points and crossing the 70% mIoU threshold for the first time.
Dynamic Graph CNN for Learning on Point Clouds
WangYueFt/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.
PointCNN: Convolution On $\mathcal{X}$-Transformed Points
yangyanli/PointCNN
•
•
NeurIPS 2018
The proposed method is a generalization of typical CNNs to feature learning from point clouds, thus we call it PointCNN.
PCT: Point cloud transformer
MenghaoGuo/PCT
•
•
It is inherently permutation invariant for processing a sequence of points, making it well-suited for point cloud learning.
KPConv: Flexible and Deformable Convolution for Point Clouds
HuguesTHOMAS/KPConv
•
•
ICCV 2019
Furthermore, these locations are continuous in space and can be learned by the network.
PointConv: Deep Convolutional Networks on 3D Point Clouds
DylanWusee/pointconv
•
•
CVPR 2019
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.
Submanifold Sparse Convolutional Networks
facebookresearch/SparseConvNet
•
•
Convolutional network are the de-facto standard for analysing spatio-temporal data such as images, videos, 3D shapes, etc.
Relation-Shape Convolutional Neural Network for Point Cloud Analysis
Yochengliu/Relation-Shape-CNN
•
•
CVPR 2019
Specifically, the convolutional weight for local point set is forced to learn a high-level relation expression from predefined geometric priors, between a sampled point from this point set and the others.
Masked Autoencoders for Point Cloud Self-supervised Learning
Then, a standard Transformer based autoencoder, with an asymmetric design and a shifting mask tokens operation, learns high-level latent features from unmasked point patches, aiming to reconstruct the masked point patches.
