Beautification of images by generative adversarial networks

被引：1

作者：

Music, Amar ^{[1
]}

Maerten, Anne-Sofie ^{[1
]}

Wagemans, Johan ^{[1
]}

机构：

[1] Katholieke Univ Leuven, Dept Brain & Cognit, Leuven, Belgium

来源：

JOURNAL OF VISION | 2023年 / 23卷 / 10期

基金：

欧洲研究理事会;

关键词：

computational aesthetics; image preference; image beautification; generative adversarial networks; low-level image features; mid-level image features; aesthetic experience questionnaire; R PACKAGE;

D O I：

10.1167/jov.23.10.14

中图分类号：

R77 [眼科学];

学科分类号：

100212 ;

摘要：

Finding the properties underlying beauty has always been a prominent yet difficult problem. However, new technological developments have often aided scientific progress by expanding the scientists' toolkit. Currently in the spotlight of cognitive neuroscience and vision science are deep neural networks. In this study, we have used a generative adversarial network (GAN) to generate images of increasing aesthetic value. We validated that this network indeed was able to increase the aesthetic value of an image by letting participants decide which of two presented images they considered more beautiful. As our validation was successful, we were justified to use the generated images to extract low- and mid-level features contributing to their aesthetic value. We compared the brightness, contrast, sharpness, saturation, symmetry, colorfulness, and visual complexity levels of "low-aesthetic" images to those of "high-aesthetic" images. We found that all of these features increased for the beautiful images, implying that they may play an important role underlying the aesthetic value of an image. With this study, we have provided further evidence for the potential value GANs may have for research concerning beauty.

引用

页数：21

共 50 条

[21] FamilyGAN: Generating Kin Face Images Using Generative Adversarial Networks [J].

Sinha, Raunak ;

Vatsa, Mayank ;

Singh, Richa .

COMPUTER VISION - ECCV 2020 WORKSHOPS, PT III, 2020, 12537 :297-311

[22] Generative adversarial networks for reconstructing natural images from brain activity [J].

Seeliger, K. ;

Guclu, U. ;

Ambrogioni, L. ;

Gucluturk, Y. ;

van Gerven, M. A. J. .

NEUROIMAGE, 2018, 181 :775-785

[23] Super Resolution of Car Plate Images Using Generative Adversarial Networks [J].

Lai, Tan Kean ;

Abbas, Aymen F. ;

Abdu, Aliyu M. ;

Sheikh, Usman U. ;

Mokji, Musa ;

Khalil, Kamal .

2019 IEEE 15TH INTERNATIONAL COLLOQUIUM ON SIGNAL PROCESSING & ITS APPLICATIONS (CSPA 2019), 2019, :80-85

[24] Correction of Banding Errors in Satellite Images With Generative Adversarial Networks (GAN) [J].

Paola, Zarate L. ;

Jesus, Lopez S. ;

Christian, Arroyo H. ;

Sonia, Rincon U. .

IEEE ACCESS, 2023, 11 :51960-51970

[25] Deriving map images of generalised mountain roads with generative adversarial networks [J].

Courtial, Azelle ;

Touya, Guillaume ;

Zhang, Xiang .

INTERNATIONAL JOURNAL OF GEOGRAPHICAL INFORMATION SCIENCE, 2023, 37 (03) :499-528

[26] Nuclei Counting in Microscopy Images With Three Dimensional Generative Adversarial Networks [J].

Han, Shuo ;

Lee, Soonam ;

Fu, Chichen ;

Salama, Paul ;

Dunn, Kenneth W. ;

Delp, Edward J. .

MEDICAL IMAGING 2019: IMAGE PROCESSING, 2019, 10949

[27] Exploring generative adversarial networks and adversarial training [J].

Sajeeda A. ;

Hossain B.M.M. .

Int. J. Cogn. Comp. Eng., (78-89) :78-89

[28] Steganographic Generative Adversarial Networks [J].

Volkhonskiy, Denis ;

Nazarov, Ivan ;

Burnaev, Evgeny .

TWELFTH INTERNATIONAL CONFERENCE ON MACHINE VISION (ICMV 2019), 2020, 11433

[29] A survey of generative adversarial networks [J].

Zhu, Kongtao ;

Liu, Xiwei ;

Yang, Hongxue .

2018 CHINESE AUTOMATION CONGRESS (CAC), 2018, :2768-2773

[30] Coevolution of Generative Adversarial Networks [J].

Costa, Victor ;

Lourenco, Nuno ;

Machado, Penousal .

APPLICATIONS OF EVOLUTIONARY COMPUTATION, EVOAPPLICATIONS 2019, 2019, 11454 :473-487

← 1 2 3 4 5 →