Unusual Transformation: A Deep Learning Approach to Create Art

In this research, we proposed the concept of “unusual transformation,” which realizes transformation between two very different image sets as an extension of CycleGAN. CycleGAN is a new deep-learning-based AI technology that can realize transformation between two image sets. Although conventional Cy...

Mô tả chi tiết

Lưu vào:
Hiển thị chi tiết
Tác giả chính: Mai, Cong Hung, Mai, Xuan Trang, Ryohei, Nakatsu, Naoko, Tosa
Định dạng: Bài trích
Ngôn ngữ:English
Nhà xuất bản: Springer 2022
Chủ đề:
Truy cập trực tuyến:https://link.springer.com/chapter/10.1007/978-3-030-95531-1_21
https://dlib.phenikaa-uni.edu.vn/handle/PNK/5871
https://doi.org/10.1007/978-3-030-95531-1_21
Từ khóa: Thêm từ khóa
Không có từ khóa, Hãy là người đầu tiên đánh dấu biểu ghi này!
id oai:localhost:PNK-5871
record_format dspace
spelling oai:localhost:PNK-58712022-08-17T05:54:54Z Unusual Transformation: A Deep Learning Approach to Create Art Mai, Cong Hung Mai, Xuan Trang Ryohei, Nakatsu Naoko, Tosa GANs CycleGAN In this research, we proposed the concept of “unusual transformation,” which realizes transformation between two very different image sets as an extension of CycleGAN. CycleGAN is a new deep-learning-based AI technology that can realize transformation between two image sets. Although conventional CycleGAN researchers have tried transformation between two similar image sets, we applied CycleGAN to the transformation of two very different image sets such as between portraits photos and Ikebana or Shan-Shui paintings. Then to obtain a better result, we improved CycleGAN by adding a new loss function and developed “UTGAN (Unusual Transformation GAN).” We found that by using UTGAN, portrait photos and animal photos are transformed into Ikabana-like and Shan-Shui-like images. Then we carried out an analysis of the obtained result and made a hypothesis that the unusual transformation works well because both Ikebana and Shan-Shui are fundamental and abstracted expressions of nature. Also, we carried out various considerations to justify the hypothesis. 2022-07-13T01:59:46Z 2022-07-13T01:59:46Z 2022 Bài trích https://link.springer.com/chapter/10.1007/978-3-030-95531-1_21 https://dlib.phenikaa-uni.edu.vn/handle/PNK/5871 https://doi.org/10.1007/978-3-030-95531-1_21 en Springer
institution Digital Phenikaa
collection Digital Phenikaa
language English
topic GANs
CycleGAN
spellingShingle GANs
CycleGAN
Mai, Cong Hung
Mai, Xuan Trang
Ryohei, Nakatsu
Naoko, Tosa
Unusual Transformation: A Deep Learning Approach to Create Art
description In this research, we proposed the concept of “unusual transformation,” which realizes transformation between two very different image sets as an extension of CycleGAN. CycleGAN is a new deep-learning-based AI technology that can realize transformation between two image sets. Although conventional CycleGAN researchers have tried transformation between two similar image sets, we applied CycleGAN to the transformation of two very different image sets such as between portraits photos and Ikebana or Shan-Shui paintings. Then to obtain a better result, we improved CycleGAN by adding a new loss function and developed “UTGAN (Unusual Transformation GAN).” We found that by using UTGAN, portrait photos and animal photos are transformed into Ikabana-like and Shan-Shui-like images. Then we carried out an analysis of the obtained result and made a hypothesis that the unusual transformation works well because both Ikebana and Shan-Shui are fundamental and abstracted expressions of nature. Also, we carried out various considerations to justify the hypothesis.
format Bài trích
author Mai, Cong Hung
Mai, Xuan Trang
Ryohei, Nakatsu
Naoko, Tosa
author_facet Mai, Cong Hung
Mai, Xuan Trang
Ryohei, Nakatsu
Naoko, Tosa
author_sort Mai, Cong Hung
title Unusual Transformation: A Deep Learning Approach to Create Art
title_short Unusual Transformation: A Deep Learning Approach to Create Art
title_full Unusual Transformation: A Deep Learning Approach to Create Art
title_fullStr Unusual Transformation: A Deep Learning Approach to Create Art
title_full_unstemmed Unusual Transformation: A Deep Learning Approach to Create Art
title_sort unusual transformation: a deep learning approach to create art
publisher Springer
publishDate 2022
url https://link.springer.com/chapter/10.1007/978-3-030-95531-1_21
https://dlib.phenikaa-uni.edu.vn/handle/PNK/5871
https://doi.org/10.1007/978-3-030-95531-1_21
_version_ 1751856285401219072
score 8.891145