SOTAVerified

Bird's-Eye View Semantic Segmentation

Papers

Showing 125 of 26 papers

TitleStatusHype
SimBEV: A Synthetic Multi-Task Multi-Sensor Driving Data Generation Tool and DatasetCode1
Epipolar Attention Field Transformers for Bird's Eye View Semantic Segmentation0
Progressive Query Refinement Framework for Bird's-Eye-View Semantic Segmentation from Surrounding ImagesCode0
Uncertainty Quantification for Bird's Eye View Semantic Segmentation: Methods and Benchmarks0
Improving Bird's Eye View Semantic Segmentation by Task DecompositionCode0
Residual Graph Convolutional Network for Bird's-Eye-View Semantic Segmentation0
PointBeV: A Sparse Approach to BeV PredictionsCode0
Semi-Supervised Learning for Visual Bird's Eye View Semantic SegmentationCode1
A Cross-Scale Hierarchical Transformer with Correspondence-Augmented Attention for inferring Bird's-Eye-View Semantic Segmentation0
TBP-Former: Learning Temporal Bird's-Eye-View Pyramid for Joint Perception and Prediction in Vision-Centric Autonomous Driving0
BAEFormer: Bi-Directional and Early Interaction Transformers for Bird's Eye View Semantic Segmentation0
MatrixVT: Efficient Multi-Camera to BEV Transformation for 3D PerceptionCode2
Model-Based Imitation Learning for Urban DrivingCode2
ST-P3: End-to-end Vision-based Autonomous Driving via Spatial-Temporal Feature LearningCode2
CoBEVT: Cooperative Bird's Eye View Semantic Segmentation with Sparse TransformersCode2
LaRa: Latents and Rays for Multi-Camera Bird's-Eye-View Semantic SegmentationCode1
Simple-BEV: What Really Matters for Multi-Sensor BEV Perception?Code0
PETRv2: A Unified Framework for 3D Perception from Multi-Camera ImagesCode3
Cross-view Transformers for real-time Map-view Semantic SegmentationCode1
BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal TransformersCode4
BEVSegFormer: Bird's Eye View Semantic Segmentation From Arbitrary Camera Rigs0
FIERY: Future Instance Prediction in Bird's-Eye View from Surround Monocular CamerasCode1
Lift, Splat, Shoot: Encoding Images From Arbitrary Camera Rigs by Implicitly Unprojecting to 3DCode2
BEV-Seg: Bird's Eye View Semantic Segmentation Using Geometry and Semantic Point Cloud0
LandCover.ai: Dataset for Automatic Mapping of Buildings, Woodlands, Water and Roads from Aerial ImageryCode1
Show:102550
← PrevPage 1 of 2Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1PETRv2IoU lane - 224x480 - 100x100 at 0.544.8Unverified
2MatrixVTIoU lane - 224x480 - 100x100 at 0.544.8Unverified
3PointBeVIoU veh - 224x480 - Vis filter. - 100x100 at 0.544.7Unverified
4PointBeV (static)IoU veh - 224x480 - Vis filter. - 100x100 at 0.544Unverified
5Simple-BEVIoU veh - 224x480 - Vis filter. - 100x100 at 0.543Unverified
6BEVFormerIoU veh - 224x480 - Vis filter. - 100x100 at 0.542Unverified
7FIERY (static)IoU veh - 224x480 - Vis filter. - 100x100 at 0.539.8Unverified
8LaRaIoU veh - 224x480 - Vis filter. - 100x100 at 0.538.9Unverified
9BAEFormerIoU veh - 224x480 - Vis filter. - 100x100 at 0.538.9Unverified
10FIERYIoU veh - 224x480 - No vis filter - 100x100 at 0.538.2Unverified
#ModelMetricClaimedVerifiedStatus
1PointBeV (EfficientNet-b4)IoU vehicle - 224x480 - Long45.4Unverified
2PointBeV (ResNet-50)IoU vehicle - 224x480 - Long44.5Unverified
3BEVFormer (EfficientNet-b4)IoU vehicle - 224x480 - Long44.5Unverified
4Simple-BEV (EfficientNet-b4)IoU vehicle - 224x480 - Long44.5Unverified
5Simple-BEV (ResNet-50)IoU vehicle - 224x480 - Long43.6Unverified
6BEVFormer(ResNet-50)IoU vehicle - 224x480 - Long43.2Unverified
7FIERYIoU vehicle - 224x480 - Long36.7Unverified
#ModelMetricClaimedVerifiedStatus
1BEVFusionmIoU0.5Unverified
2UniTRmIoU0.5Unverified
3BEVFusion-LmIoU0.48Unverified
4UniTR+LSSmIoU0.48Unverified
5BEVFusion-CmIoU0.15Unverified