Home News Latest Papers Tutorials Datasets Wiki SOTA LLM Models GPU Leaderboard Events

English

Supervised Only 3D Point Cloud Classification

Metrics

Number of params (M)

Overall Accuracy (PB_T50_RS)

Results

Performance results of various models on this benchmark

Model Name	Number of params (M)	Overall Accuracy (PB_T50_RS)	Paper Title	Repository
Point-PN	0.8	87.1	Parameter is Not All You Need: Starting from Non-Parametric Networks for 3D Point Cloud Analysis
PointNet	3.5	68.0	PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
Mamba3D	16.9	92.64	Mamba3D: Enhancing Local Features for 3D Point Cloud Analysis via State Space Model
PCM	34.2	88.1	Point Cloud Mamba: Point Cloud Learning via State Space Model
DeLA	5.3	90.4	Decoupled Local Aggregation for Point Cloud Learning
SPoTr	1.7	88.6	Self-positioning Point-based Transformer for Point Cloud Understanding
DGCNN	1.8	78.1	Dynamic Graph CNN for Learning on Point Clouds
Transformer	22.1	77.24	Attention Is All You Need
PointMLP	12.6	85.4	Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Framework
PointNet++	1.5	77.9	PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space
Mamba3D (no voting)	16.9	91.81	Mamba3D: Enhancing Local Features for 3D Point Cloud Analysis via State Space Model
PointNeXt	1.4	87.8	PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategies

0 of 12 row(s) selected.