Bird S Eye View Semantic Segmentation On

Metrics

IoU veh - 224x480 - No vis filter - 100x50 at 0.25

Results

Performance results of various models on this benchmark

		Paper Title
VED	8.8	Monocular Semantic Occupancy Grid Mapping with Convolutional Variational Encoder-Decoder Networks
M^2BEV	-	-
CVT	-	Cross-view Transformers for real-time Map-view Semantic Segmentation
PointBeV (static)	-	PointBeV: A Sparse Approach to BeV Predictions
TBP-Former	-	TBP-Former: Learning Temporal Bird's-Eye-View Pyramid for Joint Perception and Prediction in Vision-Centric Autonomous Driving
PETRv2	-	PETRv2: A Unified Framework for 3D Perception from Multi-Camera Images
MatrixVT	-	MatrixVT: Efficient Multi-Camera to BEV Transformation for 3D Perception
Simple-BEV	-	Simple-BEV: What Really Matters for Multi-Sensor BEV Perception?
TBP-Former (static)	-	TBP-Former: Learning Temporal Bird's-Eye-View Pyramid for Joint Perception and Prediction in Vision-Centric Autonomous Driving
LaRa	-	LaRa: Latents and Rays for Multi-Camera Bird's-Eye-View Semantic Segmentation
Lift-Splat-Shoot	-	Lift, Splat, Shoot: Encoding Images From Arbitrary Camera Rigs by Implicitly Unprojecting to 3D
PointBeV	-	PointBeV: A Sparse Approach to BeV Predictions
FIERY (static)	-	FIERY: Future Instance Prediction in Bird's-Eye View from Surround Monocular Cameras
BAEFormer	-	BAEFormer: Bi-Directional and Early Interaction Transformers for Bird's Eye View Semantic Segmentation
BEVFormer	-	BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformers
FIERY	41.1	FIERY: Future Instance Prediction in Bird's-Eye View from Surround Monocular Cameras
ST-P3	-	ST-P3: End-to-end Vision-based Autonomous Driving via Spatial-Temporal Feature Learning

0 of 17 row(s) selected.