HyperAI초신경

Semantic Segmentation On Semantic3D

평가 지표

mIoU

평가 결과

이 벤치마크에서 각 모델의 성능 결과

		Paper Title
Feature Geometric Net	78.2%	FG-Net: Fast Large-Scale LiDAR Point Clouds Understanding Network Leveraging Correlated Feature Mining and Geometric-Aware Modelling
RFCR	77.8%	Omni-supervised Point Cloud Segmentation via Gradual Receptive Field Component Reasoning
SCF-Net	77.6%	SCF-Net: Learning Spatial Contextual Features for Large-Scale Point Cloud Segmentation
RandLA-Net	77.4%	RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Clouds
SPG	76.2%	Large-scale Point Cloud Semantic Segmentation with Superpoint Graphs
BAAF-Net	75.4%	Semantic Segmentation for Real Point Cloud Scenes via Bilateral Augmentation and Adaptive Fusion
KPConv	74.6%	KPConv: Flexible and Deformable Convolution for Point Clouds
SPG	73.2%	Large-scale Point Cloud Semantic Segmentation with Superpoint Graphs
GACNet	70.8%	Graph Attention Convolution for Point Cloud Semantic Segmentation
shellnet_v2	69.3%	ShellNet: Efficient Point Cloud Convolutional Neural Networks using Concentric Shells Statistics
MSDeepVoxNet	65.3%	Classification of Point Cloud Scenes with Multiscale Voxel Deep Network
RF_MSSF	62.7%	Semantic Classification of 3D Point Clouds with Multiscale Spherical Neighborhoods
SegCloud	61.3%	SEGCloud: Semantic Segmentation of 3D Point Clouds
SnapNet_	59.1%	Unstructured point cloud semantic labelingusing deep segmentation networks
DeePr3SS	58.5%	Deep Projective 3D Semantic Segmentation
3D-FCNN-TI	58.2%	SEGCloud: Semantic Segmentation of 3D Point Clouds
TMLC-MSR	54.2%	Fast semantic segmentation of 3d point clouds with strongly varying density

0 of 17 row(s) selected.