2020
DOI: 10.1109/access.2020.3009470
|View full text |Cite
|
Sign up to set email alerts
|

Detail-Preserving CycleGAN-AdaIN Framework for Image-to-Ink Painting Translation

Abstract: Image translation tasks based on generative models have become an important research area, such as the general framework for unsupervised image translation-CycleGAN (Cycle-Consistent Generative Adversarial Networks). A typical advantage of CycleGAN is that it can realize the training of two image sets without pairing, but there are still some problems in the preservation of semantic information and the learning of specific features. In this paper, we propose the CycleGAN-AdaIN framework based on the CycleGAN m… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
8
0

Year Published

2022
2022
2024
2024

Publication Types

Select...
9
1

Relationship

0
10

Authors

Journals

citations
Cited by 23 publications
(10 citation statements)
references
References 19 publications
0
8
0
Order By: Relevance
“…e texture tracking and matching method is used for the information fusion of works of art. Firstly, the feature analysis model (x, y, z) of works of art with color features is constructed [14].…”
Section: Color Feature Region Segmentation Of Work Of Artmentioning
confidence: 99%
“…e texture tracking and matching method is used for the information fusion of works of art. Firstly, the feature analysis model (x, y, z) of works of art with color features is constructed [14].…”
Section: Color Feature Region Segmentation Of Work Of Artmentioning
confidence: 99%
“…And dynamic layer normalization (DLN) [25] relies on a neural network to generate the β and γ . And similar to the method adopted in the works [26], [27], [28], [29], VOLUME 10, 2022 the generate parameters by using a dedicated neural network dynamically in this paper.…”
Section: B Cnn Basic Approachmentioning
confidence: 98%
“…A CycleGAN-AdaIN framework is proposed to emphasize the details of generated Chinese paintings [15]. An AdaIN structure is added between the encoder and decoder of generators in the CycleGAN model to mimic the blur of real ink wash painting, and the cycle constraint between the generated painting and reconstructed photo is cancelled to encourage the model to be more daring in void-leaving and edge-emphasizing [3, 15~16].…”
Section: Models Specifically For Generating Chinese Paintingsmentioning
confidence: 99%