Full-body High-resolution Anime Generation with Progressive Structure-conditional Generative Adversarial Networks
This addresses the challenge of high-quality and structurally consistent image generation for anime character creation, though it appears incremental by building on progressive GAN methods.
The paper tackles the problem of generating full-body, high-resolution anime character images with structural consistency by proposing Progressive Structure-conditional Generative Adversarial Networks (PSGAN), achieving 1024x1024 resolution based on pose sequences.
We propose Progressive Structure-conditional Generative Adversarial Networks (PSGAN), a new framework that can generate full-body 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 1024x1024 based on target pose sequences. We also create a novel dataset containing full-body 1024x1024 high-resolution images and exact 2D pose keypoints using Unity 3D Avatar models.