Scale Invariant Multi-view Depth Estimation Network with cGAN Refinement

Chia Hung Yeh*, Yao Pao Huang, Mei Juan Chen

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contribution


In this paper we propose a deep learning based depth estimation method for monocular RGB sequences. We train a pair of encoder-decoder network to resolve depth information form image pairs and relative camera poses. To solve scale ambiguous of monocular sequences, a conditional generative adversarial network is applied. Experimental results show that the proposed method can overcome the problem of scale ambiguous and therefore is more suitable for a variety of applications.

Original languageEnglish
Title of host publicationNew Trends in Computer Technologies and Applications - 23rd International Computer Symposium, ICS 2018, Revised Selected Papers
EditorsChuan-Yu Chang, Chien-Chou Lin, Horng-Horng Lin
PublisherSpringer Verlag
Number of pages7
ISBN (Print)9789811391897
Publication statusPublished - 2019
Event23rd International Computer Symposium, ICS 2018 - Yunlin, Taiwan
Duration: 2018 Dec 202018 Dec 22

Publication series

NameCommunications in Computer and Information Science
ISSN (Print)1865-0929
ISSN (Electronic)1865-0937


Conference23rd International Computer Symposium, ICS 2018


  • Conditional generative adversarial network
  • Deep learning
  • Multi-view depth estimation

ASJC Scopus subject areas

  • General Computer Science
  • General Mathematics


Dive into the research topics of 'Scale Invariant Multi-view Depth Estimation Network with cGAN Refinement'. Together they form a unique fingerprint.

Cite this