The CVPR 2019 Workshop on Autonomous Driving — beyond single frame perception builds on the 2018 one with a focus on multi-frame perception, prediction, and planning for autonomous driving. It aims to get together researchers and engineers from academia and industries to discuss computer vision applications in autonomous driving. In this one day workshop, we will have invited speakers, panel discussions, and technical benchmark challenges to present the current state of the art, as well as the limitations and future directions for computer vision in autonomous driving, arguably the most promising application of computer vision and AI in general.


We will host a challenge to understand the current status of computer vision algorithms in solving the environmental perception problems for autonomous driving. We have prepared new large-scale datasets with fine annotation, collected and annotated by Baidu Inc. Based on the datasets, we have defined three realistic problems and encourage new algorithms and pipelines to be invented for autonomous driving. More specifically, they are

(1) 3D Lidar object detection

(2) 3D Lidar object tracking

(3) Trajectory prediction

Participation details can be found at

Invited Speaker

Dinesh Manocha, University of Maryland

Raia Hadsell, Deepmind

Nicolas Papernot, Google Brain

Adrien Gaidon, Toyota Research Institute

Xiaoming Liu, Michigan State University

Hongdong Li, Australian National University

March 15th
June 11th
Workshop: June 16th, 2019