HyperAIHyperAI超神経

Command Palette

Search for a command to run...

プラットフォーム

3D Point Cloud Classification On Modelnet40

評価指標

Overall Accuracy

評価結果

このベンチマークにおける各モデルのパフォーマンス結果

Paper Title
PointGST95.3Parameter-Efficient Fine-Tuning in Spectral Domain for Point Cloud Learning
Mamba3D + Point-MAE95.1Mamba3D: Enhancing Local Features for 3D Point Cloud Analysis via State Space Model
ReCon++95.0ShapeLLM: Universal 3D Object Understanding for Embodied Interaction
PointGPT94.9-
point2vec94.8Point2Vec for Self-Supervised Representation Learning on Point Clouds
RepSurf-U94.7Surface Representation for Point Clouds
ReCon94.7Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative Pretraining
ULIP + PointMLP94.7ULIP: Learning a Unified Representation of Language, Images, and Point Clouds for 3D Understanding
OTMae3D94.5-
PointMLP+HyCoRe94.5Rethinking the compositionality of point clouds through regularization in the hyperbolic space
PointMLP94.5Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Framework
Point-FEMAE94.5Towards Compact 3D Representations via Point Feature Enhancement Masked Autoencoders
PointNet2+PointCMT94.4Let Images Give You More:Point Cloud Cross-Modal Training for Shape Analysis
IDPT94.4Instance-aware Dynamic Prompt Tuning for Pre-trained Point Cloud Models
OTMae3D (w/o Voting)94.3-
PTv294.2Point Transformer V2: Grouped Vector Attention and Partition-based Pooling
PCP-MAE94.2PCP-MAE: Learning to Predict Centers for Point Masked Autoencoders
ExpPoint-MAE94.2ExpPoint-MAE: Better interpretability and performance for self-supervised point cloud transformers
IAE + DGCNN94.2Implicit Autoencoder for Point-Cloud Self-Supervised Representation Learning
CurveNet94.2Walk in the Cloud: Learning Curves for Point Clouds Shape Analysis
0 of 110 row(s) selected.