Towards many-to-one neural style transfer method
| Autor: | Michal Bogacz, Marcin Iwanowski |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
Flexibility (engineering)
Painting business.industry Computer science Deep learning ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION Process (computing) Convolutional neural network GeneralLiterature_MISCELLANEOUS Style (sociolinguistics) Image (mathematics) Transfer (computing) Computer vision Artificial intelligence business ComputingMethodologies_COMPUTERGRAPHICS |
| Zdroj: | HSI |
| Popis: | Neural style transfer aims at transforming the artistic style of a painting into a photograph. The classic methods are based on the one-to-one principle, where stylization is performed based on a single style image. In the paper, an approach is proposed that allows transferring the style based on multiple images of the same reference painter multiplied, in addition, by data augmentation. Comparing to the original method, the proposed approach produces visibly better results, and allows for greater flexibility in the transferring process. The proposed many-to-one method is illustrated by an example of transferring the style of two Polish painters using the same content image |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|