paper-with-me

nuScenes

홈페이지 · 논문 2,139편

The nuScenes dataset is a large-scale autonomous driving dataset. The dataset has 3D bounding boxes for 1000 scenes collected in Boston and Singapore. Each scene is 20 seconds long and annotated at 2Hz. This results in a total of 28130 samples for training, 6019 samples for validation and 6008 samples for testing. The dataset has the full autonomous vehicle data suite: 32-beam LiDAR, 6 cameras and radars with complete 360° coverage. The 3D object detection challenge evaluates the performance on 10 classes: cars, trucks, buses, trailers, construction vehicles, pedestrians, motorcycles, bicycles, traffic cones and barriers. Source: PointPainting: Sequential Fusion for 3D Object Detection

Images3DPoint cloudTrackingLiDAR

벤치마크

3D Object Detection on nuScenes 결과 2238개

3D Multi-Object Tracking on nuScenes 결과 345개

3D Object Detection on nuScenes Camera Only 결과 114개

3D Object Detection on nuscenes Camera-Radar 결과 66개

Bird's-Eye View Semantic Segmentation on nuScenes 결과 51개

LIDAR Semantic Segmentation on nuScenes 결과 36개

Trajectory Prediction on nuScenes 결과 35개

Semi-Supervised Semantic Segmentation on nuScenes 결과 22개

Object Detection on nuScenes 결과 13개

3D Multi-Object Tracking on nuscenes Camera-Radar 결과 12개

Trajectory Planning on nuScenes 결과 12개

3D Semantic Segmentation on nuScenes 결과 9개

Lane Detection on nuScenes 결과 6개

Monocular 3D Object Detection on nuScenes 결과 6개

3D Multi-Object Tracking on nuScenes Camera Only 결과 3개

HD semantic map learning on nuScenes 결과 2개

Motion Detection on nuScenes 결과 2개

Instance Segmentation on nuScenes 결과 1개

Motion Planning on nuScenes 결과 1개

Online Vectorized HD Map Construction on nuScenes Camera Only 결과 1개

Prediction Of Occupancy Grid Maps on nuScenes 결과 1개