HyperAIHyperAI

Command Palette

Search for a command to run...

Console

3D Part Segmentation On Shapenet Part

Metrics

Class Average IoU
Instance Average IoU

Results

Performance results of various models on this benchmark

Paper Title
GeomGCNN-89.1Exploiting Local Geometry for Feature and Graph Construction for Better 3D Point Cloud Processing with Graph Neural Networks
Ours-88.1Beyond local patches: Preserving global–local interactions by enhancing self-attention via 3D point cloud tokenization
AVS-Net85.787.3AVS-Net: Point Sampling with Adaptive Voxel Size for 3D Scene Understanding
SPoTr85.487.2Self-positioning Point-based Transformer for Point Cloud Understanding
Diffusion Unit85.287.1Diffusion Unit: Interpretable Edge Enhancement and Suppression Learning for 3D Point Cloud Segmentation
PointNeXt85.287.1PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategies
CurveNet+GAM-87.0$(0, 4)$ dualities
DeltaConv (U-ResNet)-86.9DeltaConv: Anisotropic Operators for Geometric Deep Learning on Point Clouds
PointMLP+TAP85.286.9Take-A-Photo: 3D-to-2D Generative Pre-training of Point Cloud Models
AGCN85.786.9AGCN: Adversarial Graph Convolutional Network for 3D Point Cloud Segmentation
PointVector-S(C=64)-86.9PointVector: A Vector Representation In Point Cloud Analysis
CurveNet-86.8Walk in the Cloud: Learning Curves for Point Clouds Shape Analysis
Ps-CNN83.486.8Octree guided CNN with Spherical Kernels for 3D Point Clouds
OTMae3D85.186.8-
Spherical Kernel84.986.8Spherical Kernel for Efficient Graph Convolution on 3D Point Clouds
MKConv-86.7MKConv: Multidimensional Feature Representation for Point Cloud Analysis
PointGPT84.886.6-
PointTransformer83.786.6Point Transformer
Feature Geometric Net (FG-Net)87.786.6FG-Net: Fast Large-Scale LiDAR Point Clouds Understanding Network Leveraging Correlated Feature Mining and Geometric-Aware Modelling
DeltaNet-86.6DeltaConv: Anisotropic Operators for Geometric Deep Learning on Point Clouds
0 of 67 row(s) selected.