Performance Improvement of Image-to-Image Translation with RAPGAN and RRDB (RAPGAN와 RRDB를 이용한 Image-to-Image Translation의 성능 개선)

DongSikYoon (윤동식); Noyoon Kwak (곽노윤)

doi:10.20465/KIOTS.2023.9.1.131

Performance Improvement of Image-to-Image Translation with RAPGAN and RRDB

Journal of Internet of Things and Convergence
Abbr : JKIOTS
2023, 9(1), pp.131-138
DOI : 10.20465/KIOTS.2023.9.1.131
Publisher : The Korea Internet of Things Society
Research Area : Engineering > Computer Science > Internet Information Processing
Received : November 16, 2022
Accepted : December 30, 2022
Published : February 28, 2023

DongSikYoon ¹, Noyoon Kwak ²

¹고려대학교
²백석대학교

Accredited

ABSTRACT

This paper is related to performance improvement of Image-to-Image translation using Relativistic Average Patch GAN and Residual in Residual Dense Block. The purpose of this paper is to improve performance through technical improvements in three aspects to compensate for the shortcomings of the previous pix2pix, a type of Image-to-Image translation. First, unlike the previous pix2pix constructor, it enables deeper learning by using Residual in Residual Block in the part of encoding the input image. Second, since we use a loss function based on Relativistic Average Patch GAN to predict how real the original image is compared to the generated image, both of these images affect adversarial generative learning. Finally, the generator is pre-trained to prevent the discriminator from being learned prematurely. According to the proposed method, it was possible to generate images superior to the previous pix2pix by more than 13% on average at the aspect of FID.

KEYWORDS

GAN, pix2pix, Conditional GAN, RRDB, Relativistic Average Patch GAN

Citation status

* References for papers published after 2023 are currently being built.

[confproc] I. Goodfellow / 2014 / Generative Adversarial Nets / Proceedings of Conference on Neural Information Processing Systems

[confproc] P. Isola / 2017 / Image-to-Image Translation with Conditional Adversarial Networks / Proceedings of Conference on Computer Vision and Pattern Recognition

[other] M. Mirza / 2014 / Conditional Generative Adversarial Nets / arXiv: 1411.1784

[confproc] T. Wang / 2018 / High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs / Proceedings of Conference on Computer Vision and Pattern Recognition

[confproc] X. Wang / 2018 / ESRGAN : Enhanced Super-resolution Generative Adversarial Networks / Proceedings of European Conference on Computer Vision : 63~79

[confproc] D. Bashkirova / 2019 / Adversarial Self-Defense for Cycle-Consistent GANs / Proceedings of Conference on Neural Information Processing Systems

[confproc] T. Bepler / 2019 / Explicitly Disentangling Image Content from Translation and Rotation with Spatial-VAE / Proceedings of Conference on Neural Information Processing Systems

[confproc] Y. Alharbi / 2019 / Latent Filter Scaling for Multimodal Unsupervised Image-to-Image Translation / Proceedings of Conference on Computer Vision and Pattern Recognition

[confproc] Tycho F. A. van der Ouderaa / 2019 / Reversible GANs for Memory-efficient Image-to-Image Translation / Proceedings of Conference on Computer Vision and Pattern Recognition

[other] K. Frans / 2018 / Unsupervised Image to Sequence Translation with Canvas-Drawer Networks / arXiv preprint arXiv : 1809. 08340

[confproc] Z. Murez / 2018 / Image to Image Translation for Domain Adaptation / Proceedings of Conference on Computer Vision and Pattern Recognition

[confproc] J. Zhu / 2017 / Toward Multimodal Image-to-Image Translation / Proceedings of Conference on Neural Information Processing Systems

[confproc] M. Liu / 2017 / Unsupervised Image-to-Image Translation Networks / Proceedings of Conference on Neural Information Processing Systems

[confproc] B. Lim / 2017 / Enhanced Deep Residual Networks for Single Image Super-resolution / Proceedings of Conference on Computer Vision and Pattern Recognition

[confproc] Y. Zhang / 2018 / Residual Dense Network for Image Super-resolution / Proceedings of Conference on Computer Vision and Pattern Recognition

[other] A. Jolicoeur-Martineau / 2018 / The Relativistic Discriminator : A Key Element Missing from Standard GAN / arXiv preprint arXiv : 1807. 00734

This paper was written with support from the National Research Foundation of Korea.

KJCKorea
Journal Central

Journal of Internet of Things and Convergence 2023 KCI Impact Factor : 0.89

Performance Improvement of Image-to-Image Translation with RAPGAN and RRDB

ABSTRACT

KEYWORDS

Citation status

* References for papers published after 2023 are currently being built.

Journal of Internet of Things and Convergence 2023 KCI Impact Factor : 0.89

Performance Improvement of Image-to-Image Translation with RAPGAN and RRDB

ABSTRACT

KEYWORDS

Statistics

Tools

Issue List

Citation status

KCI Citation Counts (0)

REFERENCES (16) * References for papers published after 2023 are currently being built.

Search PDF

Citation

* References for papers published after 2023 are currently being built.