South Korean Game Developer’s AI Turns Your Selfie Into an Anime Face

Author : RikiRangga
Publish Date : 2021-05-23 21:21:37
South Korean Game Developer’s AI Turns Your Selfie Into an Anime Face

Many anime and cartoon fans use anime profile pictures to represent themselves in a virtual world of social media, games and online forums.

Now, such avatars can be personalized. Last month a team of South Korean researchers proposed a method that uses unsupervised image translation to transform a simple selfie into a classic Japanese-style anime face.
The novel “U-GAT-IT” method generates visually superior results compared with previous cutting-edge techniques. The TensorFlow implementation of the paper has been released in a GitHub project:
 

https://smucommons.instructure.com/eportfolios/2003/Home/Film_completoITALIANO_Fast__Furious_9_2021_Film__ita_Altadefinizione
https://episcopalacademy.instructure.com/eportfolios/2358/Home/OPENLOAD_Fast__Furious_9_2021_Film_Completo_Italiano_Streaming_Gratis
https://tea.instructure.com/eportfolios/160093/Home/Fast__Furious_9__The_Fast_Saga_streaming_ita__Film_completo_italiano_SENZALIMITI
https://calswec.instructure.com/eportfolios/7696/Home/Guarda_lintero_Fast__Furious_9_2021_italiano_HD_Stream_online
https://canvas.laurea.fi/eportfolios/26715/Home/Fast__Furious_9_Film_completo_italiano_2021_

The creation of generative adversarial networks (GANs) in 2014 laid the foundation for a wide range of image synthesis applications, and one of the most high-profile among them is image translation. Researchers can either use supervised learning to learn a mapping model from paired data samples, or use unsupervised learning to learn a shared latent space and cycle consistency assumptions.
A unsolved challenge in image translation is improving GAN model performance when translating between images that significantly vary in shape — such as from cats to dogs or from selfies to cartoons.
That is addressed by the innovation in this paper: an end-to-end framework that incorporates a new attention module and Adaptive Layer-Instance Normalization (AdaLIN). The attention modules are embedded in both the generator and the discriminator, and identify discriminative image regions in source and target images. Researchers trained an auxiliary classifier on the importance weights of the feature map, which then generated a set of attention maps to guide the model to focus on important regions, such as eyes and mouths.

The AdaLIN, which is applied to the decoder of the generator, can help the model flexibly control degrees of change in shape and texture without adjusting the model architecture or the hyperparameters.
Researchers compared the U-GAT-IT model with CycleGAN, UNIT, MUNIT, and DRIT on five unpaired image datasets — selfie2anime, horse2zebra and photo2vangogh, and cat2dog and photo2portrait. They used different evaluation metrics to assess model performance. In one evaluation, 135 human judges were presented with translated results from different methods and asked to choose their favourites. The U-GAT-IT model significantly surpassed other models on four datasets. The results are shown below.

Do you dream of Asuna Yuuki? Do you long to escape to a fantasy world with a beautiful anime partner? If so there’s a new artificial intelligence system just for you — the “Waifu Vending Machine” can create a highly customized anime companion in minutes.
“Waifu” is a Japanese term for a fictional heartthrob in manga/anime/gaming culture. Many fans casually refer to their favourite female character in a game or anime as their Waifu, while some take it a step further, treating Waifu as an essential part of their lives. The term is increasingly widespread globally as Japanese otaku culture continues to deeply resonate among Millennials.
The AI-powered Waifu Vending Machine first randomly creates 16 fictional female characters from scratch. Users can choose one to proceed to the next step, or refresh the grid if none of the generated characters tickle their fancy.


Researchers also employed quantitate evaluations using Kernel Inception Distance (KID). Lower KID scores suggest more shared visual similarities between real and fake images. Below are the experiment results.

Three of the paper’s authors — Junho Kim, Minjae Kim, and Hyeonwoo Kang — are from NCSoft, the South Korean video game giant best known for its role playing game series Lineage. NCSOFT has been doubling down on AI since 2011 when it launched its AI and Natural Language Processing (NLP) Center. Last year the company introduced an AI system powered by reinforcement learning to battle human professional players in its homegrown game Blade & Soul.
For more information, read the paper U-GAT-IT: Unsupervised Generative Attentional Networks with Adaptive Layer-Instance Normalization for Image-to-Image Translation on arXiv.
Journalist: Tony Peng | Editor: Michael Sarazen
We know you don’t want to miss any stories. Subscribe to our popular Synced Global AI Weekly to get weekly AI updates.

Need a comprehensive review of the past, present and future of modern AI research development
 



Category : entertainment

Watch Obama, Shaq, and Charles Barkley team up to combat Black vaccine hesitancy in new video

Watch Obama, Shaq, and Charles Barkley team up to combat Black vaccine hesitancy in new video

- Professor Eddie Glaude shares story of losing close friend to Covid IE 11 is not supported. For an optimal experience visit our site


Though some studies like that Hanushek (2011)

Though some studies like that Hanushek (2011)

- Though some studies like that Hanushek (2011) have suggested that the experience positively influences teacher quality only in the first few years


VERIFY: Brood X is coming. Heres what the cicadas look like now, and your top questions answered

VERIFY: Brood X is coming. Heres what the cicadas look like now, and your top questions answered

- Professor Eddie Glaude shares story of losing close friend to Covid IE 11 is not supported. For an optimal experience visit our site


Travel the World on a Budget

Travel the World on a Budget

- Travel the World on a BudgetTravel the World on a BudgetTravel the World on a BudgetTravel the World on a Budget