Lidar Semantic Segmentation On Paris Lille 3D

Métriques

mIOU

Résultats

Résultats de performance de divers modèles sur ce benchmark

		Paper Title
FKAConv	0.827	FKAConv: Feature-Kernel Alignment for Point Cloud Convolution
Feature Geometric Net (FG Net)	0.819	FG-Net: Fast Large-Scale LiDAR Point Clouds Understanding Network Leveraging Correlated Feature Mining and Geometric-Aware Modelling
GeomGCNN	0.785	Exploiting Local Geometry for Feature and Graph Construction for Better 3D Point Cloud Processing with Graph Neural Networks
ConvPoint	0.759	ConvPoint: Continuous Convolutions for Point Cloud Processing
KPConv deform	0.759	KPConv: Flexible and Deformable Convolution for Point Clouds
CLOUDSPAM	0.738	CLOUDSPAM: Contrastive Learning On Unlabeled Data for Segmentation and Pre-Training Using Aggregated Point Clouds and MoCo
ConvPoint_Keras	0.720	ConvPoint: Continuous Convolutions for Point Cloud Processing
DA-supervised	0.638	CLOUDSPAM: Contrastive Learning On Unlabeled Data for Segmentation and Pre-Training Using Aggregated Point Clouds and MoCo
Paris-Lille-3D	0.31	Paris-Lille-3D: a large and high-quality ground truth urban point cloud dataset for automatic segmentation and classification

0 of 9 row(s) selected.

Lidar Semantic Segmentation On Paris Lille 3D | SOTA | HyperAI