Semantic Segmentation on nuScenes

Metric: IoU lane - 224x480 - 100x100 at 0.5 (higher is better)

LeaderboardDataset

Loading chart...

Results

Submit a result

Sort:

#	Model↕	IoU lane - 224x480 - 100x100 at 0.5▼	Extra Data	Paper	Date↕	Code
1	PointBeV (static)	49.6	No	PointBeV: A Sparse Approach to BeV Predictions	2023-12-01	Code
2	PETRv2	44.8	No	PETRv2: A Unified Framework for 3D Perception fr...	2022-06-02	Code
3	MatrixVT	44.8	No	MatrixVT: Efficient Multi-Camera to BEV Transfor...	2022-11-19	Code
4	M^2BEV	38	No	-	-	-
5	BEVFormer	25.7	No	BEVFormer: Learning Bird's-Eye-View Representati...	2022-03-31	Code

#1PointBeV (static)SOTA
49.6
IoU lane - 224x480 - 100x100 at 0.5· 2023-12-01
PointBeV: A Sparse Approach to BeV Predictions Code
#2PETRv2SOTA
44.8
IoU lane - 224x480 - 100x100 at 0.5· 2022-06-02
PETRv2: A Unified Framework for 3D Perception from Multi-Camera Images Code
#3MatrixVT
44.8
IoU lane - 224x480 - 100x100 at 0.5· 2022-11-19
MatrixVT: Efficient Multi-Camera to BEV Transformation for 3D Perception Code
#4M^2BEV
38
IoU lane - 224x480 - 100x100 at 0.5
No paper
#5BEVFormerSOTA
25.7
IoU lane - 224x480 - 100x100 at 0.5· 2022-03-31
BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformers Code