Increased-Range Unsupervised Monocular Depth Estimation

06/23/2020
by   Saad Imran, et al.
0

Unsupervised deep learning methods have shown promising performance for single-image depth estimation. Since most of these methods use binocular stereo pairs for self-supervision, the depth range is generally limited. Small-baseline stereo pairs provide small depth range but handle occlusions well. On the other hand, stereo images acquired with a wide-baseline rig cause occlusions-related errors in the near range but estimate depth well in the far range. In this work, we propose to integrate the advantages of the small and wide baselines. By training the network using three horizontally aligned views, we obtain accurate depth predictions for both close and far ranges. Our strategy allows to infer multi-baseline depth from a single image. This is unlike previous multi-baseline systems which employ more than two cameras. The qualitative and quantitative results show the superior performance of multi-baseline approach over previous stereo-based monocular methods. For 0.1 to 80 meters depth range, our approach decreases the absolute relative error of depth by 24 on a single Nvidia1080 GPU, making it useful for practical applications.

READ FULL TEXT

page 5

page 6

research
04/13/2021

Single Image Depth Estimation: An Overview

We review solutions to the problem of depth estimation, arguably the mos...
research
08/05/2018

Learning monocular depth estimation with unsupervised trinocular assumptions

Obtaining accurate depth measurements out of a single image represents a...
research
08/04/2018

T2Net: Synthetic-to-Realistic Translation for Solving Single-Image Depth Estimation Tasks

Current methods for single-image depth estimation use training datasets ...
research
11/05/2020

MorphEyes: Variable Baseline Stereo For Quadrotor Navigation

Morphable design and depth-based visual control are two upcoming trends ...
research
12/21/2020

Monocular Depth Parameterizing Networks

Monocular depth estimation is a highly challenging problem that is often...
research
08/01/2019

Physical Cue based Depth-Sensing by Color Coding with Deaberration Network

Color-coded aperture (CCA) methods can physically measure the depth of a...
research
05/22/2023

Gated Stereo: Joint Depth Estimation from Gated and Wide-Baseline Active Stereo Cues

We propose Gated Stereo, a high-resolution and long-range depth estimati...

Please sign up or login with your details

Forgot password? Click here to reset