Enhancement of Anime Imaging Enlargement using Modified Super-Resolution CNN

Intaniyom, Tanakit; Thananporn, Warinthorn; Woraratpanya, Kuntpong

doi:10.1109/icitee53064.2021.9611842

Cited by 1 publication

(1 citation statement)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In our implementation, we employ the pre-trained weight known as the "Anime face weight," which can be accessed at https://github.com/yashyenugu/Anime-Face-GAN. However, since the pre-trained weights and architecture were optimized for output sizes of 64x64 pixels, which are relatively small, we employ the super-resolution model developed by Intaniyom et al [16] to upscale the generated images from 64x64 to 256x256 pixels. It is important to note that the super-resolution model has already been trained for enhancing anime images, and the corresponding weights have been made available.…”

Section: Dcganmentioning

confidence: 99%

2D virtual YouTuber character generation using generative adversarial networks

Thedwichienchai,

Siriborvornratanakul

2024

Fifth International Conference on Computer Vision and Computational Intelligence (CVCI 2024)

View full text Add to dashboard Cite

Virtual YouTubers (VTubers) offer significant growth potential as a new type of content creator. However, the financial aspect poses a hurdle for aspiring VTubers. This article proposes a cost-effective solution by utilizing generative models to create full-body images of 2D VTuber characters. Notably, studies have achieved remarkable results using Generative Adversarial Networks (GANs), including Deep Convolutional GAN (DCGAN) and Style-based GAN 2 (StyleGAN2), for anime face generation. To address the lack of image synthesis systems for full-body anime characters, experiments were conducted with DCGAN and StyleGAN2 on the Danbooru dataset. The results demonstrate that StyleGAN2 models outperform DCGAN, yielding superior Fréchet Inception Distance (FID) scores of 25.06, 28.03, and 24.52, compared to DCGAN's 159.21 FID score. This research contributes to reducing the cost associated with becoming a VTuber and offers insights into generating 2D full-body anime characters for VTubers.

show abstract

Section: Dcganmentioning

confidence: 99%