Scale Invariant Multi-view Depth Estimation Network with cGAN Refinement

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

*此作品的通信作者

研究成果: 書貢獻/報告類型會議論文篇章

摘要

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.

原文英語
主出版物標題New Trends in Computer Technologies and Applications - 23rd International Computer Symposium, ICS 2018, Revised Selected Papers
編輯Chuan-Yu Chang, Chien-Chou Lin, Horng-Horng Lin
發行者Springer Verlag
頁面681-687
頁數7
ISBN(列印)9789811391897
DOIs
出版狀態已發佈 - 2019
事件23rd International Computer Symposium, ICS 2018 - Yunlin, 臺灣
持續時間: 2018 十二月 202018 十二月 22

出版系列

名字Communications in Computer and Information Science
1013
ISSN(列印)1865-0929
ISSN(電子)1865-0937

會議

會議23rd International Computer Symposium, ICS 2018
國家/地區臺灣
城市Yunlin
期間2018/12/202018/12/22

ASJC Scopus subject areas

  • 電腦科學(全部)
  • 數學(全部)

指紋

深入研究「Scale Invariant Multi-view Depth Estimation Network with cGAN Refinement」主題。共同形成了獨特的指紋。

引用此