3D Semantic Segmentation On Semantickitti

Métriques

test mIoU

Résultats

Résultats de performance de divers modèles sur ce benchmark

Nom du modèle	test mIoU	Paper Title	Repository
PolarNet	57.2%	PolarNet: An Improved Grid Representation for Online LiDAR Point Clouds Semantic Segmentation
PointNet++	20.1%	PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space
TangentConv	35.9%	Tangent Convolutions for Dense Prediction in 3D
BAAF-Net	59.9%	Semantic Segmentation for Real Point Cloud Scenes via Bilateral Augmentation and Adaptive Fusion
SPLATNet	18.4%	SPLATNet: Sparse Lattice Networks for Point Cloud Processing
PPT+SparseUNet	-	Towards Large-scale 3D Representation Learning with Multi-dataset Point Prompt Training
DITR	74.4%	-	-
TALoS	-	TALoS: Enhancing Semantic Scene Completion via Test-time Adaptation on the Line of Sight
TORNADONet-HiRes	63.1%	TORNADO-Net: mulTiview tOtal vaRiatioN semAntic segmentation with Diamond inceptiOn module	-
SqueezeSegV3	55.9%	SqueezeSegV3: Spatially-Adaptive Convolution for Efficient Point-Cloud Segmentation
NAPL	61.6%	Number-Adaptive Prototype Learning for 3D Point Cloud Semantic Segmentation	-
RandLA-Net	53.9%	RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Clouds
KPRNet	63.1%	KPRNet: Improving projection-based LiDAR semantic segmentation
OA-CNNs	-	OA-CNNs: Omni-Adaptive Sparse CNNs for 3D Semantic Segmentation
2DPASS	72.9%	2DPASS: 2D Priors Assisted Semantic Segmentation on LiDAR Point Clouds
FRNet	73.3%	FRNet: Frustum-Range Networks for Scalable LiDAR Segmentation
MPF	55.5%	Multi Projection Fusion for Real-time Semantic Segmentation of 3D LiDAR Point Clouds	-
PointNet	14.6%	PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
LiM3D+SDSC	-	Less is More: Reducing Task and Model Complexity for 3D Point Cloud Semantic Segmentation
Meta-RangeSeg	61.0%	Meta-RangeSeg: LiDAR Sequence Semantic Segmentation Using Multiple Feature Aggregation

0 of 46 row(s) selected.