3D Point Cloud Classification On Modelnet40

Metrics

Overall Accuracy

Results

Performance results of various models on this benchmark

		Paper Title
PointGST	95.3	Parameter-Efficient Fine-Tuning in Spectral Domain for Point Cloud Learning
Mamba3D + Point-MAE	95.1	Mamba3D: Enhancing Local Features for 3D Point Cloud Analysis via State Space Model
ReCon++	95.0	ShapeLLM: Universal 3D Object Understanding for Embodied Interaction
PointGPT	94.9	-
point2vec	94.8	Point2Vec for Self-Supervised Representation Learning on Point Clouds
RepSurf-U	94.7	Surface Representation for Point Clouds
ReCon	94.7	Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative Pretraining
ULIP + PointMLP	94.7	ULIP: Learning a Unified Representation of Language, Images, and Point Clouds for 3D Understanding
OTMae3D	94.5	-
PointMLP+HyCoRe	94.5	Rethinking the compositionality of point clouds through regularization in the hyperbolic space
PointMLP	94.5	Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Framework
Point-FEMAE	94.5	Towards Compact 3D Representations via Point Feature Enhancement Masked Autoencoders
PointNet2+PointCMT	94.4	Let Images Give You More:Point Cloud Cross-Modal Training for Shape Analysis
IDPT	94.4	Instance-aware Dynamic Prompt Tuning for Pre-trained Point Cloud Models
OTMae3D (w/o Voting)	94.3	-
PTv2	94.2	Point Transformer V2: Grouped Vector Attention and Partition-based Pooling
PCP-MAE	94.2	PCP-MAE: Learning to Predict Centers for Point Masked Autoencoders
ExpPoint-MAE	94.2	ExpPoint-MAE: Better interpretability and performance for self-supervised point cloud transformers
IAE + DGCNN	94.2	Implicit Autoencoder for Point-Cloud Self-Supervised Representation Learning
CurveNet	94.2	Walk in the Cloud: Learning Curves for Point Clouds Shape Analysis

0 of 110 row(s) selected.

Command Palette

3D Point Cloud Classification On Modelnet40

Metrics

Results