3D Point Cloud Classification On Modelnet40

Metrics

Overall Accuracy

Results

Performance results of various models on this benchmark

Model Name	Overall Accuracy	Paper Title	Repository
PCNN	92.3	Point Convolutional Neural Networks by Extension Operators
Point Cloud Transformer	93.2	PCT: Point cloud transformer
PointNet2+PointCMT	94.4	Let Images Give You More:Point Cloud Cross-Modal Training for Shape Analysis
Point-MAE	94.0	Masked Autoencoders for Point Cloud Self-supervised Learning
PointConT	93.5	Point Cloud Classification Using Content-based Transformer via Clustering in Feature Space
InterpCNN	93.0	Interpolated Convolutional Networks for 3D Point Cloud Understanding	-
point2vec	94.8	Point2Vec for Self-Supervised Representation Learning on Point Clouds
RS-CNN	92.9	Relation-Shape Convolutional Neural Network for Point Cloud Analysis
PointNet++	90.7	PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space
DSPoint	93.5	DSPoint: Dual-scale Point Cloud Recognition with High-frequency Fusion
GBNet	93.8	Geometric Back-projection Network for Point Cloud Classification	-
PointNet + SageMix	90.3	SageMix: Saliency-Guided Mixup for Point Clouds
Point-M2AE	94.0	Point-M2AE: Multi-scale Masked Autoencoders for Hierarchical Point Cloud Pre-training
Point-PN	93.8	Parameter is Not All You Need: Starting from Non-Parametric Networks for 3D Point Cloud Analysis
APES (local-based downsample)	93.5	Attention-based Point Cloud Edge Sampling
PointGPT	94.9	-	-
PointNeXt	94.0	PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategies
Perceiver	-	Perceiver: General Perception with Iterative Attention
GDANet	93.8	Learning Geometry-Disentangled Representation for Complementary Understanding of 3D Object Point Cloud
VRN (single view)	-	Generative and Discriminative Voxel Modeling with Convolutional Neural Networks

0 of 110 row(s) selected.