nuScenes: A multimodal dataset for autonomous driving

26 Mar 2019Holger CaesarVarun BankitiAlex H. LangSourabh VoraVenice Erin LiongQiang XuAnush KrishnanYu PanGiancarlo BaldanOscar Beijbom

Robust detection and tracking of objects is crucial for the deployment of autonomous vehicle technology. Image-based benchmark datasets have driven the development in computer vision tasks such as object detection, tracking and segmentation of agents in the environment... (read more)

PDF Abstract

Evaluation results from the paper


Task Dataset Model Metric name Metric value Global rank Uses extra
training data
Compare
3D Object Detection nuScenes PointPillars NDS 44.2 # 4
3D Object Detection nuScenes PointPillars (ImageNet) NDS 44.9 # 2
3D Object Detection nuScenes PointPillars (KITTI) NDS 44.8 # 3