Next Article in Journal
Classification of Factors Affecting the Performance of Fully Grouted Rock Bolts with Empirical Classification Systems
Previous Article in Journal
Analogy Study of Center-Of-Pressure and Acceleration Measurement for Evaluating Human Body Balance via Segmentalized Principal Component Analysis
Open AccessArticle

Image-To-Image Translation Using a Cross-Domain Auto-Encoder and Decoder

Department of Computer Science, Hanyang University, Seoul 04763, Korea
*
Author to whom correspondence should be addressed.
Appl. Sci. 2019, 9(22), 4780; https://doi.org/10.3390/app9224780
Received: 11 October 2019 / Revised: 31 October 2019 / Accepted: 5 November 2019 / Published: 8 November 2019
(This article belongs to the Section Computing and Artificial Intelligence)
Recently, several studies have focused on image-to-image translation. However, the quality of the translation results is lacking in certain respects. We propose a new image-to-image translation method to minimize such shortcomings using an auto-encoder and an auto-decoder. This method includes pre-training two auto-encoders and decoder pairs for each source and target image domain, cross-connecting two pairs and adding a feature mapping layer. Our method is quite simple and straightforward to adopt but very effective in practice, and we experimentally demonstrated that our method can significantly enhance the quality of image-to-image translation. We used the well-known cityscapes, horse2zebra, cat2dog, maps, summer2winter, and night2day datasets. Our method shows qualitative and quantitative improvements over existing models. View Full-Text
Keywords: image-to-image translation; encoder-decoder; deep learning; feature mapping layer image-to-image translation; encoder-decoder; deep learning; feature mapping layer
Show Figures

Graphical abstract

MDPI and ACS Style

Yoo, J.; Eom, H.; Choi, Y.S. Image-To-Image Translation Using a Cross-Domain Auto-Encoder and Decoder. Appl. Sci. 2019, 9, 4780.

Show more citation formats Show less citations formats
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
  • Externally hosted supplementary file 1
    Doi: 10.5281/zenodo.3479932
    Link: https://zenodo.org/record/3479932
    Description: Supplementary files (test set inputs and results) for "IMAGE-TO-IMAGE TRANSLATION USING A CROSS-DOMAIN AUTO-ENCODER AND DECODER"
Back to TopTop