Supervised Only 3D Point Cloud Classification

Metriken

Number of params (M)

Overall Accuracy (PB_T50_RS)

Ergebnisse

Leistungsergebnisse verschiedener Modelle zu diesem Benchmark

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

0 of 12 row(s) selected.

Supervised Only 3D Point Cloud Classification | SOTA | HyperAI