← Bird's-Eye View Semantic Segmentation

Papers with Code · CC BY-SA 4.0

nuScenes

아카이브 평가 17건 · 마지막 적재/변경 2026-10-30

원본 데이터셋 링크 1

평가 기록

과거 수집 기록이며 최신 순위가 아닙니다. 데이터셋 버전·split·실험 조건과 지표 방향이 검증되지 않은 결과는 직접 비교할 수 없습니다. 날짜는 논문 날짜이며 최신 평가일을 뜻하지 않습니다.

표가 화면보다 넓으면 좌우로 스크롤하여 논문과 구현 링크를 확인하세요.

원본 기록 순서 · 순위 미부여
모델	원본 지표·값	논문	구현
PointBeV	IoU veh - 224x480 - No vis filter - 100x100 at 0.5 39.9 IoU veh - 448x800 - No vis filter - 100x100 at 0.5 43.2 IoU veh - 224x480 - Vis filter. - 100x100 at 0.5 44.7 IoU veh - 448x800 - Vis filter. - 100x100 at 0.5 48.7 IoU ped - 224x480 - Vis filter. - 100x100 at 0.5 19.9	PointBeV: A Sparse Approach to BeV Predictions 2023-12-01	코드 1
PointBeV (static)	IoU veh - 224x480 - No vis filter - 100x100 at 0.5 38.7 IoU veh - 448x800 - No vis filter - 100x100 at 0.5 42.1 IoU veh - 224x480 - Vis filter. - 100x100 at 0.5 44.0 IoU veh - 448x800 - Vis filter. - 100x100 at 0.5 47.6 IoU ped - 224x480 - Vis filter. - 100x100 at 0.5 18.5 IoU lane - 224x480 - 100x100 at 0.5 49.6	PointBeV: A Sparse Approach to BeV Predictions 2023-12-01	코드 1
Simple-BEV	IoU veh - 224x480 - No vis filter - 100x100 at 0.5 36.9 IoU veh - 448x800 - No vis filter - 100x100 at 0.5 40.9 IoU veh - 224x480 - Vis filter. - 100x100 at 0.5 43.0 IoU veh - 448x800 - Vis filter. - 100x100 at 0.5 46.6	Simple-BEV: What Really Matters for Multi-Sensor BEV Perception? 2022-06-16	코드 1
BEVFormer	IoU veh - 224x480 - No vis filter - 100x100 at 0.5 35.8 IoU veh - 448x800 - No vis filter - 100x100 at 0.5 39.0 IoU veh - 224x480 - Vis filter. - 100x100 at 0.5 42.0 IoU veh - 448x800 - Vis filter. - 100x100 at 0.5 45.5 IoU lane - 224x480 - 100x100 at 0.5 25.7	BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformers 2022-03-31	코드 1 · 코드 2 · 코드 3
FIERY (static)	IoU veh - 224x480 - No vis filter - 100x100 at 0.5 35.8 IoU veh - 224x480 - Vis filter. - 100x100 at 0.5 39.8 IoU ped - 224x480 - Vis filter. - 100x100 at 0.5 17.2	FIERY: Future Instance Prediction in Bird's-Eye View from Surround Monocular Cameras 2021-04-21	코드 1
BAEFormer	IoU veh - 224x480 - No vis filter - 100x100 at 0.5 36 IoU veh - 448x800 - No vis filter - 100x100 at 0.5 37.8 IoU veh - 224x480 - Vis filter. - 100x100 at 0.5 38.9 IoU veh - 448x800 - Vis filter. - 100x100 at 0.5 41.0	BAEFormer: Bi-Directional and Early Interaction Transformers for Bird's Eye View Semantic Segmentation 2023-01-01	연결 없음
LaRa	IoU veh - 224x480 - No vis filter - 100x100 at 0.5 35.4 IoU veh - 224x480 - Vis filter. - 100x100 at 0.5 38.9	LaRa: Latents and Rays for Multi-Camera Bird's-Eye-View Semantic Segmentation 2022-06-27	코드 1
CVT	IoU veh - 224x480 - No vis filter - 100x100 at 0.5 31.4 IoU veh - 448x800 - No vis filter - 100x100 at 0.5 32.5 IoU veh - 224x480 - Vis filter. - 100x100 at 0.5 36.0 IoU veh - 448x800 - Vis filter. - 100x100 at 0.5 37.7	Cross-view Transformers for real-time Map-view Semantic Segmentation 2022-05-05	코드 1 · 코드 2
FIERY	IoU veh - 224x480 - No vis filter - 100x50 at 0.25 41.1 IoU veh - 224x480 - No vis filter - 100x100 at 0.5 38.2 IoU vehicle - Setting 3 58.5	FIERY: Future Instance Prediction in Bird's-Eye View from Surround Monocular Cameras 2021-04-21	코드 1
TBP-Former	IoU ped - 224x480 - Vis filter. - 100x100 at 0.5 18.6	TBP-Former: Learning Temporal Bird's-Eye-View Pyramid for Joint Perception and Prediction in Vision-Centric Autonomous Driving 2023-03-17	연결 없음
TBP-Former (static)	IoU ped - 224x480 - Vis filter. - 100x100 at 0.5 17.2	TBP-Former: Learning Temporal Bird's-Eye-View Pyramid for Joint Perception and Prediction in Vision-Centric Autonomous Driving 2023-03-17	연결 없음
Lift-Splat-Shoot	IoU ped - 224x480 - Vis filter. - 100x100 at 0.5 15.0	Lift, Splat, Shoot: Encoding Images From Arbitrary Camera Rigs by Implicitly Unprojecting to 3D 2020-08-13	코드 1
ST-P3	IoU ped - 224x480 - Vis filter. - 100x100 at 0.5 14.5	ST-P3: End-to-end Vision-based Autonomous Driving via Spatial-Temporal Feature Learning 2022-07-15	코드 1
PETRv2	IoU lane - 224x480 - 100x100 at 0.5 44.8	PETRv2: A Unified Framework for 3D Perception from Multi-Camera Images 2022-06-02	코드 1
MatrixVT	IoU lane - 224x480 - 100x100 at 0.5 44.8	MatrixVT: Efficient Multi-Camera to BEV Transformation for 3D Perception 2022-11-19	코드 1 · 코드 2
M^2BEV	IoU lane - 224x480 - 100x100 at 0.5 38.0	연결 없음 논문 날짜 미기재	연결 없음
VED	IoU veh - 224x480 - No vis filter - 100x50 at 0.25 8.8	Monocular Semantic Occupancy Grid Mapping with Convolutional Variational Encoder-Decoder Networks 2018-04-06	연결 없음