Unsupervised Learning of Monocular Depth Estimation and Visual Odometry with Deep Feature Reconstruction

CVPR 2018 Huangying ZhanRavi GargChamara Saroj WeerasekeraKejie LiHarsh AgarwalIan Reid

Despite learning based methods showing promising results in single view depth estimation and visual odometry, most existing approaches treat the tasks in a supervised manner. Recent approaches to single view depth estimation explore the possibility of learning without full supervision via minimizing photometric error... (read more)

PDF Abstract

Evaluation results from the paper


  Submit results from this paper to get state-of-the-art GitHub badges and help community compare results to other papers.