Single-Stage Refinement CNN for Depth Estimation in Monocular Images

Authors

  • José E. Valdez Rodríguez Instituto Politécnico Nacional, Centro de Investigación en Computación
  • Hiram Calvo Instituto Politécnico Nacional, Centro de Investigación en Computación
  • Edgardo M. Felipe Riverón Instituto Politécnico Nacional, Centro de Investigación en Computación

DOI:

https://doi.org/10.13053/cys-24-2-3370

Keywords:

Depth reconstruction, convolutional neural networks, single stage training, embedded refinement layer, stereo matching

Abstract

Depth reconstruction from single monocular images has been a challenging task due to the complexity and the quantity of depth cues that images have. Convolutional Neural Networks (CNN) have been successfully used to reconstruct depth of general object scenes; however, proposed works use several stages of training which make this process more complex and time consuming. As we aim to build a computational efficient model, we focus on single-stage training CNN. In this paper, we propose five different models for solving this task, ranging from a simple convolutional network, to one with residual, convolutional, refinement and upsampling layers. We compare our models with the current state of the art in depth reconstruction and measure depth reconstruction error for different datasets (KITTI, NYU), obtaining improvements in both global and local error measures.

Downloads

Published

2020-06-23

Issue

Vol. 24 No. 2 (2020): Thematic Issue on Language & Knowledge Engineering (Guest editors: D. Pinto, B. Beltrán, A. Vázquez)

Section

Articles of the Thematic Issue

License 

Hereby I transfer exclusively to the Journal "Computación y 
Sistemas", published by the Computing Research Center (CIC-IPN),
the Copyright of the aforementioned paper. I also accept that these 
rights will not be transferred to any other publication, in any other 
format, language or other existing means of developing.
I certify that the paper has not been previously disclosed or simultaneo
usly submitted to any other publication, and that it does not contain 
material whose publication would violate the Copyright or other 
proprietary rights of any person, company or institution. I certify that 
I have the permission from the institution or company where I work or 
study to publish this work.
The representative author accepts the responsibility for the publication
of this paper on behalf of each and every one of the authors. 
This transfer is subject to the following conditions:
  • The authors retain all ownership rights (such as patent rights) of this work, except for the publishing rights transferred to the CIC, through this document.
  • Authors retain the right to publish the work in whole or in part in any book they are the authors or publishers. They can also make use of this work in conferences, courses, personal web pages, and so on.
  • Authors may include working as part of his thesis, for non-profit distribution only.