Pseudo Supervised Monocular Depth Estimation with Teacher-Student Network

TL;DR

This paper introduces a pseudo supervision approach using a teacher-student network for monocular depth estimation, leveraging binocular disparity as pseudo ground truth to improve accuracy without requiring pixel-wise annotations.

Contribution

It presents a novel unsupervised method that combines binocular and monocular depth estimation via knowledge distillation, enhancing monocular depth accuracy.

Findings

Outperforms state-of-the-art on KITTI benchmark

Effectively converts unsupervised learning to supervised via pseudo ground truth

Utilizes binocular disparity to improve monocular depth estimation

Abstract

Despite recent improvement of supervised monocular depth estimation, the lack of high quality pixel-wise ground truth annotations has become a major hurdle for further progress. In this work, we propose a new unsupervised depth estimation method based on pseudo supervision mechanism by training a teacher-student network with knowledge distillation. It strategically integrates the advantages of supervised and unsupervised monocular depth estimation, as well as unsupervised binocular depth estimation. Specifically, the teacher network takes advantage of the effectiveness of binocular depth estimation to produce accurate disparity maps, which are then used as the pseudo ground truth to train the student network for monocular depth estimation. This effectively converts the problem of unsupervised learning to supervised learning. Our extensive experimental results demonstrate that the proposed method outperforms the state-of-the-art on the KITTI benchmark.