GAN‐based tone curve learning for colour transfer
Abstract A new approach for reflecting the colour tone of a reference image on the input image is proposed. Depending on the source and reference image pairs, conventional statistical colour transfer methods often lead to undesirable colour transfer. Conversely, deep learning methods depend on prior...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2022-08-01
|
| Series: | Electronics Letters |
| Online Access: | https://doi.org/10.1049/ell2.12547 |
| _version_ | 1818501574596493312 |
|---|---|
| author | D. Ito R. Sasaki K. Uruma |
| author_facet | D. Ito R. Sasaki K. Uruma |
| author_sort | D. Ito |
| collection | DOAJ |
| description | Abstract A new approach for reflecting the colour tone of a reference image on the input image is proposed. Depending on the source and reference image pairs, conventional statistical colour transfer methods often lead to undesirable colour transfer. Conversely, deep learning methods depend on prior learning, which results in unnatural output images when inappropriate images are learned; moreover, in such situations, analysing what kind of colour transformation has actually been performed is difficult. This state of the art motivates the proposal of a new colour transfer method that estimates tone curves based on generative adversarial nets. This method does not require any data set other than input and reference images, thus enabling a more appropriate colour transfer. The superior output of the proposed method compared with some baseline approaches is demonstrated through experiments. |
| first_indexed | 2024-12-10T20:58:10Z |
| format | Article |
| id | doaj.art-94a8392c6e2345ac9ab2990df655c5f2 |
| institution | Directory Open Access Journal |
| issn | 0013-5194 1350-911X |
| language | English |
| last_indexed | 2024-12-10T20:58:10Z |
| publishDate | 2022-08-01 |
| publisher | Wiley |
| record_format | Article |
| series | Electronics Letters |
| spelling | doaj.art-94a8392c6e2345ac9ab2990df655c5f22022-12-22T01:33:55ZengWileyElectronics Letters0013-51941350-911X2022-08-01581660961110.1049/ell2.12547GAN‐based tone curve learning for colour transferD. Ito0R. Sasaki1K. Uruma2Graduate School of Informatics Kogakuin University Tokyo JapanSchool of Computer Science Tokyo University of Technology Tokyo JapanDepartment of Computer Science Kogakuin University Tokyo JapanAbstract A new approach for reflecting the colour tone of a reference image on the input image is proposed. Depending on the source and reference image pairs, conventional statistical colour transfer methods often lead to undesirable colour transfer. Conversely, deep learning methods depend on prior learning, which results in unnatural output images when inappropriate images are learned; moreover, in such situations, analysing what kind of colour transformation has actually been performed is difficult. This state of the art motivates the proposal of a new colour transfer method that estimates tone curves based on generative adversarial nets. This method does not require any data set other than input and reference images, thus enabling a more appropriate colour transfer. The superior output of the proposed method compared with some baseline approaches is demonstrated through experiments.https://doi.org/10.1049/ell2.12547 |
| spellingShingle | D. Ito R. Sasaki K. Uruma GAN‐based tone curve learning for colour transfer Electronics Letters |
| title | GAN‐based tone curve learning for colour transfer |
| title_full | GAN‐based tone curve learning for colour transfer |
| title_fullStr | GAN‐based tone curve learning for colour transfer |
| title_full_unstemmed | GAN‐based tone curve learning for colour transfer |
| title_short | GAN‐based tone curve learning for colour transfer |
| title_sort | gan based tone curve learning for colour transfer |
| url | https://doi.org/10.1049/ell2.12547 |
| work_keys_str_mv | AT dito ganbasedtonecurvelearningforcolourtransfer AT rsasaki ganbasedtonecurvelearningforcolourtransfer AT kuruma ganbasedtonecurvelearningforcolourtransfer |