Illustrated Character Face Super-Deformation via Unsupervised Image-to-Image Translation
Abstract: In this study, we introduce a novel image generation task: the super-deformation of character images. We also propose a GAN training framework that does not require paired supervision. Experimental results confirm that the proposed method produces more natural and semantically appropriate super-deformed images than conventional approaches.
Authors: Tomoya Sawada, Marie Katsurai
Publication venue: Multimedia Systems
Demo
Code and Reference
https://github.com/STomoya/ChibiGAN
Sawada, T., Katsurai, M. Illustrated character face super-deformation via unsupervised image-to-image translation. Multimedia Systems 30, 63 (2024). https://doi.org/10.1007/s00530-023-01255-y