OpenCodePapers

bird-s-eye-view-semantic-segmentation-on

Bird's-Eye View Semantic Segmentation
Dataset Link
Results over time
Click legend items to toggle metrics. Hover points for model names.
Leaderboard
PaperCodeIoU veh - 224x480 - Vis filter. - 100x100 at 0.5IoU veh - 448x800 - Vis filter. - 100x100 at 0.5IoU veh - 224x480 - No vis filter - 100x100 at 0.5IoU veh - 448x800 - No vis filter - 100x100 at 0.5IoU ped - 224x480 - Vis filter. - 100x100 at 0.5IoU lane - 224x480 - 100x100 at 0.5IoU veh - 224x480 - No vis filter - 100x50 at 0.25IoU vehicle - Setting 3ModelNameReleaseDate
PointBeV: A Sparse Approach to BeV Predictions✓ Link44.748.739.943.219.9PointBeV2023-12-01
PointBeV: A Sparse Approach to BeV Predictions✓ Link44.047.638.742.118.549.6PointBeV (static)2023-12-01
Simple-BEV: What Really Matters for Multi-Sensor BEV Perception?✓ Link43.046.636.940.9Simple-BEV2022-06-16
BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformers✓ Link42.045.535.839.025.7BEVFormer2022-03-31
FIERY: Future Instance Prediction in Bird's-Eye View from Surround Monocular Cameras✓ Link39.835.817.2FIERY (static)2021-04-21
BAEFormer: Bi-Directional and Early Interaction Transformers for Bird's Eye View Semantic Segmentation38.941.03637.8BAEFormer2023-01-01
LaRa: Latents and Rays for Multi-Camera Bird's-Eye-View Semantic Segmentation✓ Link38.935.4LaRa2022-06-27
Cross-view Transformers for real-time Map-view Semantic Segmentation✓ Link36.037.731.432.5CVT2022-05-05
FIERY: Future Instance Prediction in Bird's-Eye View from Surround Monocular Cameras✓ Link38.241.158.5FIERY2021-04-21
TBP-Former: Learning Temporal Bird's-Eye-View Pyramid for Joint Perception and Prediction in Vision-Centric Autonomous Driving18.6TBP-Former2023-03-17
TBP-Former: Learning Temporal Bird's-Eye-View Pyramid for Joint Perception and Prediction in Vision-Centric Autonomous Driving17.2TBP-Former (static)2023-03-17
Lift, Splat, Shoot: Encoding Images From Arbitrary Camera Rigs by Implicitly Unprojecting to 3D✓ Link15.0Lift-Splat-Shoot2020-08-13
ST-P3: End-to-end Vision-based Autonomous Driving via Spatial-Temporal Feature Learning✓ Link14.5ST-P32022-07-15
PETRv2: A Unified Framework for 3D Perception from Multi-Camera Images✓ Link44.8PETRv22022-06-02
MatrixVT: Efficient Multi-Camera to BEV Transformation for 3D Perception✓ Link44.8MatrixVT2022-11-19
[]()38.0M^2BEV
Monocular Semantic Occupancy Grid Mapping with Convolutional Variational Encoder-Decoder Networks8.8VED2018-04-06