HyperAI超神経
ホームニュース最新論文チュートリアルデータセット百科事典SOTALLMモデルGPU ランキング学会
検索
サイトについて
HyperAI超神経

Supervised Only 3D Point Cloud Classification

評価指標

Number of params (M)
Overall Accuracy (PB_T50_RS)

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

モデル名
Number of params (M)
Overall Accuracy (PB_T50_RS)
Paper TitleRepository
Point-PN0.887.1Parameter is Not All You Need: Starting from Non-Parametric Networks for 3D Point Cloud Analysis
PointNet3.568.0PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
Mamba3D16.992.64Mamba3D: Enhancing Local Features for 3D Point Cloud Analysis via State Space Model
PCM34.288.1Point Cloud Mamba: Point Cloud Learning via State Space Model
DeLA5.390.4Decoupled Local Aggregation for Point Cloud Learning
SPoTr1.788.6Self-positioning Point-based Transformer for Point Cloud Understanding
DGCNN1.878.1Dynamic Graph CNN for Learning on Point Clouds
Transformer22.177.24Attention Is All You Need
PointMLP12.685.4Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Framework
PointNet++1.577.9PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space
Mamba3D (no voting)16.991.81Mamba3D: Enhancing Local Features for 3D Point Cloud Analysis via State Space Model
PointNeXt1.487.8PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategies
0 of 12 row(s) selected.