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

## TL;DR

This paper introduces an unsupervised framework that jointly learns monocular depth estimation and visual odometry from stereo sequences, leveraging deep feature reconstruction to improve accuracy and scale consistency.

## Contribution

It proposes a novel unsupervised learning approach using stereo sequences and deep feature warping, enhancing depth and odometry estimation without full supervision.

## Key findings

- Joint training improves depth prediction accuracy.
- Deep feature-based warping outperforms simple photometric warping.
- Method surpasses existing learning-based methods on KITTI dataset.

## Abstract

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. In this paper, we explore the use of stereo sequences for learning depth and visual odometry. The use of stereo sequences enables the use of both spatial (between left-right pairs) and temporal (forward backward) photometric warp error, and constrains the scene depth and camera motion to be in a common, real-world scale. At test time our framework is able to estimate single view depth and two-view odometry from a monocular sequence. We also show how we can improve on a standard photometric warp loss by considering a warp of deep features. We show through extensive experiments that: (i) jointly training for single view depth and visual odometry improves depth prediction because of the additional constraint imposed on depths and achieves competitive results for visual odometry; (ii) deep feature-based warping loss improves upon simple photometric warp loss for both single view depth estimation and visual odometry. Our method outperforms existing learning based methods on the KITTI driving dataset in both tasks. The source code is available at https://github.com/Huangying-Zhan/Depth-VO-Feat