DeepAI AI Chat
Log In Sign Up

SelfTune: Metrically Scaled Monocular Depth Estimation through Self-Supervised Learning

03/10/2022
by   Jaehoon Choi, et al.
University of Maryland
13

Monocular depth estimation in the wild inherently predicts depth up to an unknown scale. To resolve scale ambiguity issue, we present a learning algorithm that leverages monocular simultaneous localization and mapping (SLAM) with proprioceptive sensors. Such monocular SLAM systems can provide metrically scaled camera poses. Given these metric poses and monocular sequences, we propose a self-supervised learning method for the pre-trained supervised monocular depth networks to enable metrically scaled depth estimation. Our approach is based on a teacher-student formulation which guides our network to predict high-quality depths. We demonstrate that our approach is useful for various applications such as mobile robot navigation and is applicable to diverse environments. Our full system shows improvements over recent self-supervised depth estimation and completion methods on EuRoC, OpenLORIS, and ScanNet datasets.

READ FULL TEXT

page 1

page 5

page 6

04/14/2020

RealMonoDepth: Self-Supervised Monocular Depth Estimation for General Scenes

We present a generalised self-supervised learning approach for monocular...
09/16/2020

Calibrating Self-supervised Monocular Depth Estimation

In the recent years, many methods demonstrated the ability of neural net...
03/24/2022

Unsupervised Simultaneous Learning for Camera Re-Localization and Depth Estimation from Video

We present an unsupervised simultaneous learning framework for the task ...
09/08/2020

Self-Supervised Scale Recovery for Monocular Depth and Egomotion Estimation

The self-supervised loss formulation for jointly training depth and egom...
02/24/2022

N-QGN: Navigation Map from a Monocular Camera using Quadtree Generating Networks

Monocular depth estimation has been a popular area of research for sever...
06/20/2018

Learning what is above and what is below: horizon approach to monocular obstacle detection

A novel approach is proposed for monocular obstacle detection, which rel...
05/05/2022

FisheyeDistill: Self-Supervised Monocular Depth Estimation with Ordinal Distillation for Fisheye Cameras

In this paper, we deal with the problem of monocular depth estimation fo...