HyperAI超神经

3D Part Segmentation On Shapenet Part

评估指标

Class Average IoU
Instance Average IoU

评测结果

各个模型在此基准测试上的表现结果

模型名称
Class Average IoU
Instance Average IoU
Paper TitleRepository
InterpCNN84.086.3Interpolated Convolutional Networks for 3D Point Cloud Understanding-
Point Voxel Transformer-86.5PVT: Point-Voxel Transformer for Point Cloud Learning
Point-JEPA85.8±0.1-Point-JEPA: A Joint Embedding Predictive Architecture for Self-Supervised Learning on Point Cloud-
SSCNN82.084.7SyncSpecCNN: Synchronized Spectral CNN for 3D Shape Segmentation-
Point Cloud Transformer-86.4PCT: Point cloud transformer
DensePoint84.286.4DensePoint: Learning Densely Contextual Representation for Efficient Point Cloud Processing
CurveNet-86.8Walk in the Cloud: Learning Curves for Point Clouds Shape Analysis
3D-JEPA86.4184.933D-JEPA: A Joint Embedding Predictive Architecture for 3D Self-Supervised Representation Learning-
KPConv85.186.4KPConv: Flexible and Deformable Convolution for Point Clouds
GeomGCNN-89.1Exploiting Local Geometry for Feature and Graph Construction for Better 3D Point Cloud Processing with Graph Neural Networks-
PartNet84.1-PartNet: A Recursive Part Decomposition Network for Fine-grained and Hierarchical Shape Segmentation-
point2vec84.686.3Point2Vec for Self-Supervised Representation Learning on Point Clouds
RS-CNN-86.2Relation-Shape Convolutional Neural Network for Point Cloud Analysis
SGPN-85.8SGPN: Similarity Group Proposal Network for 3D Point Cloud Instance Segmentation
P2Sequence-85.2Point2Sequence: Learning the Shape Representation of 3D Point Clouds with an Attention-based Sequence to Sequence Network-
PointNet-83.7PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
PointGPT84.886.6--
PointGrid82.286.4PointGrid: A Deep Network for 3D Shape Understanding
DeltaConv (U-ResNet)-86.9DeltaConv: Anisotropic Operators for Geometric Deep Learning on Point Clouds
ConvPoint83.485.8ConvPoint: Continuous Convolutions for Point Cloud Processing
0 of 67 row(s) selected.