Predicting and Using Monocular Depth for Deep Driving

Adrien Gaidon1

  • 1Toyota Research Institute

Details

13:30 - 14:00 | Sun 9 Jun | Room L108 | SuDT5.7

Session: 3D-DLAD: 3D Deep Learning for Automated Driving

Abstract

Recent advances in deep learning for monocular depth prediction opens a breadth of new uses for cameras in automated driving. First, we will discuss a new model, called SuperDepth, that uses super-resolution and self-supervised learning to get state-of-the-art monocular depth. Second, we will show that these predictions are indeed useful as a prior for a new method, called ROI-10D, for 3D object detection and metric shape retrieval from a single image, vastly improving performance on the standard KITTI benchmark.