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

Lidar Semantic Segmentation On Paris Lille 3D

評価指標

mIOU

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
mIOU
Paper TitleRepository
ConvPoint0.759ConvPoint: Continuous Convolutions for Point Cloud Processing
GeomGCNN0.785Exploiting Local Geometry for Feature and Graph Construction for Better 3D Point Cloud Processing with Graph Neural Networks-
Feature Geometric Net (FG Net)0.819FG-Net: Fast Large-Scale LiDAR Point Clouds Understanding Network Leveraging Correlated Feature Mining and Geometric-Aware Modelling
Paris-Lille-3D0.31Paris-Lille-3D: a large and high-quality ground truth urban point cloud dataset for automatic segmentation and classification-
ConvPoint_Keras0.720ConvPoint: Continuous Convolutions for Point Cloud Processing
FKAConv0.827FKAConv: Feature-Kernel Alignment for Point Cloud Convolution
DA-supervised0.638CLOUDSPAM: Contrastive Learning On Unlabeled Data for Segmentation and Pre-Training Using Aggregated Point Clouds and MoCo
KPConv deform0.759KPConv: Flexible and Deformable Convolution for Point Clouds
CLOUDSPAM0.738CLOUDSPAM: Contrastive Learning On Unlabeled Data for Segmentation and Pre-Training Using Aggregated Point Clouds and MoCo
0 of 9 row(s) selected.