Bird's-Eye View Semantic Segmentation

SimBEV: A Synthetic Multi-Task Multi-Sensor Driving Data Generation Tool and Dataset

2502.01894 2025-02-04 이 페이지의 평가 5건

mIoU: 0.5road: 0.884car: 0.727truck: 0.745

PointBeV: A Sparse Approach to BeV Predictions

2312.00703 2023-12-01 이 페이지의 평가 4건

IoU veh - 224x480 - No vis filter - 100x100 at 0.5: 39.9IoU veh - 448x800 - No vis filter - 100x100 at 0.5: 43.2IoU veh - 224x480 - Vis filter. - 100x100 at 0.5: 44.7IoU veh - 448x800 - Vis filter. - 100x100 at 0.5: 48.7

BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformers

2203.17270 2022-03-31 이 페이지의 평가 3건

IoU veh - 224x480 - No vis filter - 100x100 at 0.5: 35.8IoU veh - 448x800 - No vis filter - 100x100 at 0.5: 39.0IoU veh - 224x480 - Vis filter. - 100x100 at 0.5: 42.0IoU veh - 448x800 - Vis filter. - 100x100 at 0.5: 45.5

FIERY: Future Instance Prediction in Bird's-Eye View from Surround Monocular Cameras

2104.10490 2021-04-21 이 페이지의 평가 3건

IoU veh - 224x480 - No vis filter - 100x100 at 0.5: 35.8IoU veh - 224x480 - Vis filter. - 100x100 at 0.5: 39.8IoU ped - 224x480 - Vis filter. - 100x100 at 0.5: 17.2

Simple-BEV: What Really Matters for Multi-Sensor BEV Perception?

2206.07959 2022-06-16 이 페이지의 평가 3건

IoU veh - 224x480 - No vis filter - 100x100 at 0.5: 36.9IoU veh - 448x800 - No vis filter - 100x100 at 0.5: 40.9IoU veh - 224x480 - Vis filter. - 100x100 at 0.5: 43.0IoU veh - 448x800 - Vis filter. - 100x100 at 0.5: 46.6

TBP-Former: Learning Temporal Bird's-Eye-View Pyramid for Joint Perception and Prediction in Vision-Centric Autonomous Driving

2303.09998 2023-03-17 이 페이지의 평가 2건

IoU ped - 224x480 - Vis filter. - 100x100 at 0.5: 18.6

BAEFormer: Bi-Directional and Early Interaction Transformers for Bird's Eye View Semantic Segmentation

2023-01-01 이 페이지의 평가 1건

IoU veh - 224x480 - No vis filter - 100x100 at 0.5: 36IoU veh - 448x800 - No vis filter - 100x100 at 0.5: 37.8IoU veh - 224x480 - Vis filter. - 100x100 at 0.5: 38.9IoU veh - 448x800 - Vis filter. - 100x100 at 0.5: 41.0

Cross-view Transformers for real-time Map-view Semantic Segmentation

2205.02833 2022-05-05 이 페이지의 평가 1건

IoU veh - 224x480 - No vis filter - 100x100 at 0.5: 31.4IoU veh - 448x800 - No vis filter - 100x100 at 0.5: 32.5IoU veh - 224x480 - Vis filter. - 100x100 at 0.5: 36.0IoU veh - 448x800 - Vis filter. - 100x100 at 0.5: 37.7