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

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-t...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Applied sciences Ročník 9; číslo 22; s. 4780
Hlavní autoři: Yoo, Jaechang, Eom, Heesong, Choi, Yong Suk
Médium: Journal Article
Jazyk:angličtina
Vydáno: Basel MDPI AG 01.11.2019
Témata:
deep learning
encoder-decoder
feature mapping layer
image-to-image translation
Learning
Teaching methods
Translations
ISSN:2076-3417, 2076-3417
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí: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.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:2076-3417
2076-3417
DOI:10.3390/app9224780