Unsupervised Learning of Depth and Ego-Motion from Video

TL;DR

This paper introduces an unsupervised learning approach for estimating depth and camera motion from monocular video, achieving results comparable to supervised methods without requiring ground-truth labels.

Contribution

The authors propose a novel unsupervised framework that jointly learns depth and ego-motion estimation using view synthesis as supervision, applicable independently at test time.

Findings

Depth estimation matches supervised methods on KITTI.

Pose estimation is competitive with SLAM systems.

Framework works on unstructured video sequences.

Abstract

We present an unsupervised learning framework for the task of monocular depth and camera motion estimation from unstructured video sequences. We achieve this by simultaneously training depth and camera pose estimation networks using the task of view synthesis as the supervisory signal. The networks are thus coupled via the view synthesis objective during training, but can be applied independently at test time. Empirical evaluation on the KITTI dataset demonstrates the effectiveness of our approach: 1) monocular depth performing comparably with supervised methods that use either ground-truth pose or depth for training, and 2) pose estimation performing favorably with established SLAM systems under comparable input settings.