HyperAIHyperAI
HomeConsoleDocsNewsPapersTutorialsDatasetsWikiSOTALLM ModelsGPU LeaderboardEvents
Search
About
HyperAIHyperAI

Command Palette

Search for a command to run...

3D Instance Segmentation On S3Dis

Metrics

AP@50
mAP
mCov
mPrec
mRec
mWCov

Results

Performance results of various models on this benchmark

Paper TitleRepository
ISBNet70.560.874.977.577.176.8ISBNet: a 3D Point Cloud Instance Segmentation Network with Instance-aware Sampling and Box-aware Dynamic Convolution
OneFormer3D75.863.0-82.374.1-OneFormer3D: One Transformer for Unified Point Cloud Segmentation
SSTNet67.854.1-73.573.4-Instance Segmentation in 3D Scenes using Semantic Superpoint Tree Networks
SPFormer69.2--74.071.1-Superpoint Transformer for 3D Scene Instance Segmentation
DKNet--70.375.371.172.83D Instances as 1D Kernels
MSTA3D70.0--80.670.1-MSTA3D: Multi-scale Twin-attention for 3D Instance Segmentation-
SoftGroup68.954.469.375.369.871.7SoftGroup for 3D Instance Segmentation on Point Clouds
MaskGroup69.9--66.669.6-MaskGroup: Hierarchical Point Grouping and Masking for 3D Instance Segmentation-
HAIS--67.073.269.470.4Hierarchical Aggregation for 3D Instance Segmentation
PointGroup64.0--69.669.2-PointGroup: Dual-Set Point Grouping for 3D Instance Segmentation
3D-MPA---66.764.1-3D-MPA: Multi Proposal Aggregation for 3D Semantic Instance Segmentation
JSNet--54.166.953.958JSNet: Joint Instance and Semantic Segmentation of 3D Point Clouds
SASO--54.564.250.858.3SASO: Joint 3D Semantic-Instance Segmentation via Multi-scale Semantic Association and Salient Point Clustering Optimization-
GICN---68.550.8-Learning Gaussian Instance Segmentation in Point Clouds
3D-BoNet---65.647.6-Learning Object Bounding Boxes for 3D Instance Segmentation on Point Clouds
ASIS---63.647.5-Associatively Segmenting Instances and Semantics in Point Clouds
PartNet----43.4%-PartNet: A Recursive Part Decomposition Network for Fine-grained and Hierarchical Shape Segmentation-
PBNet70.659.5----Divide and Conquer: 3D Point Cloud Instance Segmentation With Point-Wise Binarization
TD3D70.458.1----Top-Down Beats Bottom-Up in 3D Instance Segmentation-
PointCNN------PointCNN: Convolution On $\mathcal{X}$-Transformed Points
0 of 21 row(s) selected.
3D Instance Segmentation On S3Dis | SOTA | HyperAI