SOTAVerified

Bird's-Eye View Semantic Segmentation

Papers

Showing 1–26 of 26 papers

TitleStatusHype
BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal TransformersCode4
PETRv2: A Unified Framework for 3D Perception from Multi-Camera ImagesCode3
Model-Based Imitation Learning for Urban DrivingCode2
Lift, Splat, Shoot: Encoding Images From Arbitrary Camera Rigs by Implicitly Unprojecting to 3DCode2
MatrixVT: Efficient Multi-Camera to BEV Transformation for 3D PerceptionCode2
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
FIERY: Future Instance Prediction in Bird's-Eye View from Surround Monocular CamerasCode1
Semi-Supervised Learning for Visual Bird's Eye View Semantic SegmentationCode1
SimBEV: A Synthetic Multi-Task Multi-Sensor Driving Data Generation Tool and DatasetCode1
LaRa: Latents and Rays for Multi-Camera Bird's-Eye-View Semantic SegmentationCode1
Cross-view Transformers for real-time Map-view Semantic SegmentationCode1
LandCover.ai: Dataset for Automatic Mapping of Buildings, Woodlands, Water and Roads from Aerial ImageryCode1
Uncertainty Quantification for Bird's Eye View Semantic Segmentation: Methods and Benchmarks—0
Simple-BEV: What Really Matters for Multi-Sensor BEV Perception?—0
BAEFormer: Bi-Directional and Early Interaction Transformers for Bird's Eye View Semantic Segmentation—0
BEV-Seg: Bird's Eye View Semantic Segmentation Using Geometry and Semantic Point Cloud—0
BEVSegFormer: Bird's Eye View Semantic Segmentation From Arbitrary Camera Rigs—0
Epipolar Attention Field Transformers for Bird's Eye View Semantic Segmentation—0
Improving Bird's Eye View Semantic Segmentation by Task Decomposition—0
Monocular Semantic Occupancy Grid Mapping with Convolutional Variational Encoder-Decoder Networks—0
PointBeV: A Sparse Approach to BeV Predictions—0
Residual Graph Convolutional Network for Bird's-Eye-View Semantic Segmentation—0
A Cross-Scale Hierarchical Transformer with Correspondence-Augmented Attention for inferring Bird's-Eye-View Semantic Segmentation—0
TBP-Former: Learning Temporal Bird's-Eye-View Pyramid for Joint Perception and Prediction in Vision-Centric Autonomous Driving—0
Progressive Query Refinement Framework for Bird's-Eye-View Semantic Segmentation from Surrounding ImagesCode0
Show:102550

Benchmark Results

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