Full-body High-resolution Anime Generation with Progressive Structure-conditional Generative Adversarial Networks

Koichi Hamada, Kentaro Tachibana, Tianqi Li, Hiroto Honda, Yusuke Uchida; Proceedings of the European Conference on Computer Vision (ECCV) Workshops, 2018, pp. 0-0

WeproposeProgressiveStructure-conditionalGenerativeAdversarial Networks (PSGAN), a new framework that can generate fullbody and high-resolution character images based on structural information. Recent progress in generative adversarial networks with progressive training has made it possible to generate high-resolution images. However, existing approaches have limitations in achieving both high image quality and structural consistency at the same time. Our method tackles the limitations by progressively increasing the resolution of both generated images and structural conditions during training. In this paper, we empirically demonstrate the effectiveness of this method by showing the comparison with existing approaches and video generation results of diverse anime characters at 1024×1024 based on target pose sequences. We also create a novel dataset containing full-body 1024×1024 highresolution images and exact 2D pose keypoints using Unity 3D Avatar models.