Image generation step by step: animation generation-image translation

被引:5
作者
Jing, Beibei [1 ]
Ding, Hongwei [1 ]
Yang, Zhijun [1 ]
Li, Bo [1 ]
Liu, Qianlin [1 ]
机构
[1] Yunnan Univ, Sch Informat Sci & Engn, Kunming, Yunnan, Peoples R China
基金
中国国家自然科学基金;
关键词
Generative adversarial networks; LGAN (Link Generative Adversarial Networks); Unconditional generation part; Anime images conditional generation part; Super-resolution network; WASSERSTEIN DISTANCE;
D O I
10.1007/s10489-021-02835-z
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Generative adversarial networks play an important role in image generation, but the successful generation of high-resolution images from complex data sets remains a challenging goal. In this paper, we propose the LGAN (Link Generative Adversarial Networks) model, which can effectively enhance the quality of the synthesized images. The LGAN model consists of two parts, G1 and G2. G1 is responsible for the unconditional generation part, which generates anime images with highly abstract features containing few coefficients but continuous image elements covering the overall image features. Moreover, G2 is responsible for the conditional generation part (image translation), consisting of mapping and Superresolution networks. The mapping network fills the output of G1 into the real-world image after semantic segmentation or edge detection processing; the Superresolution network super-resolves the actual picture after completing mapping to improve the image's resolution. In the comparison test with WGAN, SAGAN, WGAN-GP and PG-GAN, this paper's LGAN(SEG) leads 64.36 and 12.28, respectively, fully proving the model's superiority.
引用
收藏
页码:8087 / 8100
页数:14
相关论文
共 50 条
[41]   ReFIGG: retinal fundus image generation using GAN [J].
Nair, Sharika Sasidharan ;
Meharban, M. S. .
INTERNATIONAL JOURNAL OF COMPUTATIONAL SCIENCE AND ENGINEERING, 2023, 26 (03) :316-323
[42]   Style Encoding for Class-Specific Image Generation [J].
Hochberg, Dana Cohen ;
Giryes, Raja ;
Greenspan, Hayit .
MEDICAL IMAGING 2021: IMAGE PROCESSING, 2021, 11596
[43]   Image generation and classification via generative adversarial networks [J].
Mirabedini, Shirin ;
Dastgerdi, Shadi Hejareh ;
Kangavari, Mohammadreza ;
AhmadiPanah, Mandi .
BIOSCIENCE RESEARCH, 2020, 17 (02) :1356-1363
[44]   Manifold Constraint Regularization for Remote Sensing Image Generation [J].
Su, Xingzhe ;
Zheng, Changwen ;
Qiang, Wenwen ;
Wu, Fengge ;
Zhao, Junsuo ;
Sun, Fuchun ;
Xiong, Hui .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2024, 62
[45]   Generative adversarial networks for handwriting image generation: a review [J].
Elanwar, Randa ;
Betke, Margrit .
VISUAL COMPUTER, 2025, 41 (04) :2299-2322
[46]   Diverse single image generation with controllable global structure [J].
Mahendren, Sutharsan ;
Edussooriya, Chamira U. S. ;
Rodrigo, Ranga .
NEUROCOMPUTING, 2023, 528 :97-112
[47]   Segmentation mask-guided person image generation [J].
Liu, Meichen ;
Yan, Xin ;
Wang, Chenhui ;
Wang, Kejun .
APPLIED INTELLIGENCE, 2021, 51 (02) :1161-1176
[48]   Interpreting Generative Adversarial Networks for Interactive Image Generation [J].
Zhou, Bolei .
XXAI - BEYOND EXPLAINABLE AI: International Workshop, Held in Conjunction with ICML 2020, July 18, 2020, Vienna, Austria, Revised and Extended Papers, 2022, 13200 :167-175
[49]   Image generation with self pixel-wise normalization [J].
Yoon-Jae Yeo ;
Min-Cheol Sagong ;
Seung Park ;
Sung-Jea Ko ;
Yong-Goo Shin .
Applied Intelligence, 2023, 53 :9409-9423
[50]   Image-to-Image Translation: Methods and Applications [J].
Pang, Yingxue ;
Lin, Jianxin ;
Qin, Tao ;
Chen, Zhibo .
IEEE TRANSACTIONS ON MULTIMEDIA, 2022, 24 :3859-3881