SOTAVerified

3D Semantic Segmentation

3D Semantic Segmentation is a computer vision task that involves dividing a 3D point cloud or 3D mesh into semantically meaningful parts or regions. The goal of 3D semantic segmentation is to identify and label different objects and parts within a 3D scene, which can be used for applications such as robotics, autonomous driving, and augmented reality.

Papers

Showing 150 of 348 papers

TitleStatusHype
Sonata: Self-Supervised Learning of Reliable Point RepresentationsCode4
Scalable 3D Panoptic Segmentation As Superpoint Graph ClusteringCode4
PointNeXt: Revisiting PointNet++ with Improved Training and Scaling StrategiesCode3
SGS-SLAM: Semantic Gaussian Splatting For Neural Dense SLAMCode3
FRACTAL: An Ultra-Large-Scale Aerial Lidar Dataset for 3D Semantic Segmentation of Diverse LandscapesCode3
Point Transformer V3: Simpler, Faster, StrongerCode3
Merlin: A Vision Language Foundation Model for 3D Computed TomographyCode3
Scribble-Supervised LiDAR Semantic SegmentationCode2
UniPAD: A Universal Pre-training Paradigm for Autonomous DrivingCode2
UniSeg: A Unified Multi-Modal LiDAR Segmentation Network and the OpenPCSeg CodebaseCode2
Occupancy-MAE: Self-supervised Pre-training Large-scale LiDAR Point Clouds with Masked Occupancy AutoencodersCode2
Towards Generating Realistic 3D Semantic Training Data for Autonomous DrivingCode2
FRNet: Frustum-Range Networks for Scalable LiDAR SegmentationCode2
Point Transformer V2: Grouped Vector Attention and Partition-based PoolingCode2
Spherical Transformer for LiDAR-based 3D RecognitionCode2
2DPASS: 2D Priors Assisted Semantic Segmentation on LiDAR Point CloudsCode2
STPLS3D: A Large-Scale Synthetic and Real Aerial Photogrammetry 3D Point Cloud DatasetCode2
On Deep Learning for Geometric and Semantic Scene Understanding Using On-Vehicle 3D LiDARCode2
Efficient 3D Semantic Segmentation with Superpoint TransformerCode2
PonderV2: Pave the Way for 3D Foundation Model with A Universal Pre-training ParadigmCode2
Searching Efficient 3D Architectures with Sparse Point-Voxel ConvolutionCode2
Self-supervised Learning of LiDAR 3D Point Clouds via 2D-3D Neural CalibrationCode2
OctFormer: Octree-based Transformers for 3D Point CloudsCode2
OneFormer3D: One Transformer for Unified Point Cloud SegmentationCode2
LSK3DNet: Towards Effective and Efficient 3D Perception with Large Sparse KernelsCode2
Swin UNETR: Swin Transformers for Semantic Segmentation of Brain Tumors in MRI ImagesCode2
RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point CloudsCode2
DINO in the Room: Leveraging 2D Foundation Models for 3D SegmentationCode2
ScanNet++: A High-Fidelity Dataset of 3D Indoor ScenesCode2
OpenScene: 3D Scene Understanding with Open VocabulariesCode2
Surface Representation for Point CloudsCode2
ARKit LabelMaker: A New Scale for Indoor 3D Scene UnderstandingCode2
Image-to-Lidar Self-Supervised Distillation for Autonomous Driving DataCode2
Learning Multi-View Aggregation In the Wild for Large-Scale 3D Semantic SegmentationCode2
Atlas: End-to-End 3D Scene Reconstruction from Posed ImagesCode2
4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural NetworksCode2
ODIN: A Single Model for 2D and 3D SegmentationCode2
DeepGCNs: Making GCNs Go as Deep as CNNsCode2
Fusion-then-Distillation: Toward Cross-modal Positive Distillation for Domain Adaptive 3D Semantic SegmentationCode1
ARCH2S: Dataset, Benchmark and Challenges for Learning Exterior Architectural Structures from Point CloudsCode1
GFNet: Geometric Flow Network for 3D Point Cloud Semantic SegmentationCode1
Fully Automated Scan-to-BIM Via Point Cloud Instance SegmentationCode1
GNeSF: Generalizable Neural Semantic FieldsCode1
FG-Net: Fast Large-Scale LiDAR Point Clouds Understanding Network Leveraging Correlated Feature Mining and Geometric-Aware ModellingCode1
AMAES: Augmented Masked Autoencoder Pretraining on Public Brain MRI Data for 3D-Native SegmentationCode1
FIDNet: LiDAR Point Cloud Semantic Segmentation with Fully Interpolation DecodingCode1
BuildingNet: Learning to Label 3D BuildingsCode1
Exploring Data-Efficient 3D Scene Understanding with Contrastive Scene ContextsCode1
3D Semantic Segmentation in the Wild: Learning Generalized Models for Adverse-Condition Point CloudsCode1
blob loss: instance imbalance aware loss functions for semantic segmentationCode1
Show:102550
← PrevPage 1 of 7Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1LSK3DNettest mIoU75.6Unverified
2PPT+PTv3test mIoU75.5Unverified
3UniSegtest mIoU75.2Unverified
4SphereFormertest mIoU74.8Unverified
5DITRtest mIoU74.4Unverified
6FRNettest mIoU73.3Unverified
7RangeFormertest mIoU73.3Unverified
82DPASStest mIoU72.9Unverified
9PTv2test mIoU72.6Unverified
10PPT+SparseUNetval mIoU71.4Unverified
#ModelMetricClaimedVerifiedStatus
1DITRval mIoU41.2Unverified
2ODINval mIoU40.5Unverified
3PTv3 ArKitLabelmakerval mIoU40.3Unverified
4BFANetval mIoU37.3Unverified
5Sonata + PTv3val mIoU36.8Unverified
6Pambaval mIoU36.3Unverified
7PTv3 + PPTval mIoU36Unverified
8OA-CNNsval mIoU33.3Unverified
9LSK3DNetval mIoU33.1Unverified
10OctFormerval mIoU32.6Unverified
#ModelMetricClaimedVerifiedStatus
1KPConvmIoU81.1Unverified
2Superpoint TransformermIoU79.6Unverified
3EyeNetmIoU79.6Unverified
4SuperClustermIoU77.3Unverified
5PointNet++mIoU68.3Unverified
6ConvPointmIoU67.4Unverified
7SPGmIoU60.6Unverified
8PointCNNmIoU58.4Unverified
9ShellNetmIoU57.4Unverified
#ModelMetricClaimedVerifiedStatus
1DA-supervisedmiou Val64.1Unverified
2CLOUDSPAMmiou Val63.6Unverified
3Superpoint Transformermiou Val63.5Unverified
4SuperClustermiou Val62.1Unverified
5DeepViewAggmiou58.3Unverified
6MinkowskiNetmiou53.92Unverified
7PointNet++miou35.66Unverified
8PointNetmiou13.07Unverified
#ModelMetricClaimedVerifiedStatus
1DITRTop-1 IoU0.53Unverified
2SonataTop-1 IoU0.5Unverified
3PTv3Top-1 IoU0.49Unverified
4CACTop-1 IoU0.48Unverified
5OA-CNNTop-1 IoU0.47Unverified
6OctFormerTop-1 IoU0.46Unverified
7SpUNet (MinkowskiNet)Top-1 IoU0.46Unverified
8PTv2Top-1 IoU0.45Unverified
#ModelMetricClaimedVerifiedStatus
1LCPFormermIoU63.4Unverified
2EyeNetmIoU62.3Unverified
3BEV-Seg3D-NetmIoU61.7Unverified
4KPConvmIoU57.58Unverified
5SCF-NetmIoU55.1Unverified
6SparseConvmIoU42.66Unverified
7SPGraphmIoU37.29Unverified
8TangentConvmIoU33.3Unverified
#ModelMetricClaimedVerifiedStatus
1SCF-NetOA95.5Unverified
2RandLANetOA93.5Unverified
3KPFCNNOA91.71Unverified
4TGNetOA91.64Unverified
5MS-PCNNOA91.53Unverified
6PointNet++OA91.21Unverified
7DGCNNOA89Unverified
#ModelMetricClaimedVerifiedStatus
1CSNmIOU62.1Unverified
2MID-NetmIOU60.8Unverified
3FG-NetmIOU58.2Unverified
4closerlook3DmIOU53.8Unverified
5DeepGCNmIOU45.1Unverified
6PartNetmIOU43.2Unverified
#ModelMetricClaimedVerifiedStatus
1Superpoint TransformermIoU (6-Fold)76Unverified
2OneFormer3DmIoU (Area-5)72.4Unverified
3PointTransformerV2mIoU (Area-5)71.6Unverified
4PointNextmIoU (Area-5)70.5Unverified
5PointTransformermIoU (Area-5)70.4Unverified
6PVCNN++mIoU (6-Fold)58.98Unverified
#ModelMetricClaimedVerifiedStatus
1IGNetmIoU62Unverified
2SSLSS with Cylinder3DmIoU61.3Unverified
3Cylinder3DmIoU57Unverified
4LiM3DmIoU-1%57Unverified
5LiM3D+SDSCmIoU-1%55.8Unverified
6MinkowskiNetmIoU55Unverified
#ModelMetricClaimedVerifiedStatus
1KpConvmIOU53.73Unverified
2PointCTmIOU53.2Unverified
3MinkowskiNetmIOU51.3Unverified
4SCF-NetmIOU50.65Unverified
5Point transformermIOU47.64Unverified
6PointNet++mIOU15.92Unverified
#ModelMetricClaimedVerifiedStatus
1Cylinder3DMean IoU (class)46.07Unverified
2salsanextMean IoU (class)43.07Unverified
3SphereformerMean IoU (class)42.19Unverified
4kpconvMean IoU (class)19.97Unverified
#ModelMetricClaimedVerifiedStatus
1Cylinder3DmIoU40.07Unverified
2SPVCNNmIoU36.78Unverified
3MinkUNetmIoU36.53Unverified
4SphereFormermIoU33.97Unverified
#ModelMetricClaimedVerifiedStatus
1PTv2mIoU82.6Unverified
2FRNetmIoU82.5Unverified
3AF2S3NetmIoU78.3Unverified
#ModelMetricClaimedVerifiedStatus
1PointVector-XLmIoU76.5Unverified
2PointMetaBase-XXLmIoU75.8Unverified
3PointNeXt-XLmIoU70.6Unverified
#ModelMetricClaimedVerifiedStatus
1PanopticNDT (10cm)mIoU45.43Unverified
2SemanticNDT (10cm)mIoU44.31Unverified
#ModelMetricClaimedVerifiedStatus
1DITRmIoU73.3Unverified
2vFusedSeg3DmIoU72.46Unverified
#ModelMetricClaimedVerifiedStatus
12D–3D + 3 × 3 × 3Mean IoU (test)0.45Unverified
#ModelMetricClaimedVerifiedStatus
1Res16UNet14CF10.85Unverified