We present an approach which takes advantage of both structure and semantics for unsupervised monocular learning of depth and ego-motion. More specifically, we model the motion of individual objects and learn their 3D motion vector jointly with depth and ego-motion. We obtain more accurate results, especially for challenging dynamic scenes not addressed by previous approaches. This is an extended version of Casser et al. [AAAI'19]. Code and models have been open sourced at https://sites.google.com/corp/view/struct2depth.
@article{arxiv.1906.05717,
title = {Unsupervised Monocular Depth and Ego-motion Learning with Structure and Semantics},
author = {Vincent Casser and Soeren Pirk and Reza Mahjourian and Anelia Angelova},
journal= {arXiv preprint arXiv:1906.05717},
year = {2019}
}
Comments
CVPR Workshop on Visual Odometry & Computer Vision Applications Based on Location Clues (VOCVALC), 2019. This is an extension of arXiv:1811.06152: Depth Prediction Without the Sensors: Leveraging Structure for Unsupervised Learning from Monocular Videos. Thirty-Third AAAI Conference on Artificial Intelligence (AAAI'19)