3D Instance Segmentation On Scannetv2

评估指标

mAP

mAP @ 50

mRec

评测结果

各个模型在此基准测试上的表现结果

				Paper Title	Repository
Spherical Mask	61.6	81.2	-	Spherical Mask: Coarse-to-Fine 3D Point Cloud Instance Segmentation with Spherical Representation
BFL	60.6	81.0	-	Beyond the Final Layer: Hierarchical Query Fusion Transformer with Agent-Interpolation Initialization for 3D Instance Segmentation	-
OneFromer3D	56.6	80.1	-	OneFormer3D: One Transformer for Unified Point Cloud Segmentation
MSTA3D	56.9	79.5	74.1	MSTA3D: Multi-scale Twin-attention for 3D Instance Segmentation	-
QueryFormer	58.3	78.7	-	Query Refinement Transformer for 3D Instance Segmentation	-
Mask3D	55.2	78.0	-	Mask3D: Mask Transformer for 3D Semantic Instance Segmentation
SPFormer	54.9	77.0	-	Superpoint Transformer for 3D Scene Instance Segmentation
ISBNet	55.9	76.3	-	ISBNet: a 3D Point Cloud Instance Segmentation Network with Instance-aware Sampling and Box-aware Dynamic Convolution
SoftGroup	50.4	76.1	-	SoftGroup for 3D Instance Segmentation on Point Clouds
TD3D	48.9	75.1	-	Top-Down Beats Bottom-Up in 3D Instance Segmentation	-
PBNet	57.3	74.7	-	Divide and Conquer: 3D Point Cloud Instance Segmentation With Point-Wise Binarization
DKNet	53.2	71.8	-	3D Instances as 1D Kernels
ODIN	50.0	71.0	-	ODIN: A Single Model for 2D and 3D Segmentation
HAIS	45.7	69.9	-	Hierarchical Aggregation for 3D Instance Segmentation
SSTNet	50.6	69.8	-	Instance Segmentation in 3D Scenes using Semantic Superpoint Tree Networks
MaskGroup	43.4	66.4	-	MaskGroup: Hierarchical Point Grouping and Masking for 3D Instance Segmentation	-
RPGN	42.8	64.2	-	Learning Regional Purity for Instance Segmentation on 3D Point Clouds	-
GICN	-	63.8	-	Learning Gaussian Instance Segmentation in Point Clouds
PointGroup	40.7	63.6	-	PointGroup: Dual-Set Point Grouping for 3D Instance Segmentation
HIDA	43.6	63.5	-	HIDA: Towards Holistic Indoor Understanding for the Visually Impaired via Semantic Instance Segmentation with a Wearable Solid-State LiDAR Sensor	-

0 of 31 row(s) selected.