Towards the Automatic Anime Characters Creation with Generative Adversarial Networks

Abstract

Automatic generation of facial images has been well studied after the Generative Adversarial Network (GAN) came out. There exists some attempts applying the GAN model to the problem of generating facial images of anime characters, but none of the existing work gives a promising result. In this work, we explore the training of GAN models specialized on an anime facial image dataset. We address the issue from both the data and the model aspect, by collecting a more clean, well-suited dataset and leverage proper, empirical application of DRAGAN. With quantitative analysis and case studies we demonstrate that our efforts lead to a stable and high-quality model. Moreover, to assist people with anime character design, we build a website (http://make.girls.moe) with our pre-trained model available online, which makes the model easily accessible to general public.

16 pages, 15 figures. This paper is presented as a Doujinshi in Comiket 92, summer 2017, with the booth number 05a, East-U, Third Day

References in corpus (13)

• Adam: A Method for Stochastic Optimization
• Conditional Generative Adversarial Nets
• Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
• GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
• Conditional Image Synthesis With Auxiliary Classifier GANs
• Improved Training of Wasserstein GANs
• MMD GAN: Towards Deeper Understanding of Moment Matching Network
• Towards Principled Methods for Training Generative Adversarial Networks
• The Cramer Distance as a Solution to Biased Wasserstein Gradients
• On Convergence and Stability of GANs
• Stabilizing Training of Generative Adversarial Networks through Regularization
• Loss-Sensitive Generative Adversarial Networks on Lipschitz Densities
• Activation Maximization Generative Adversarial Nets

Cited by in corpus (28)

• All One Needs to Know about Metaverse: A Complete Survey on Technological Singularity, Virtual Ecosystem, and Research Agenda
• GANSynth: Adversarial Neural Audio Synthesis
• Demystifying MMD GANs
• Deep Learning for Procedural Content Generation
• Sequential Gallery for Interactive Visual Design Optimization
• On gradient regularizers for MMD GANs
• Facial-Sketch Synthesis: A New Challenge
• Landmark Assisted CycleGAN for Cartoon Face Generation
• Encoding Invariances in Deep Generative Models
• Fit2Form: 3D Generative Model for Robot Gripper Form Design
• Twin-GAN -- Unpaired Cross-Domain Image Translation with Weight-Sharing GANs
• PI-REC: Progressive Image Reconstruction Network With Edge and Color Domain
• Dialog on a canvas with a machine
• DAF:re: A Challenging, Crowd-Sourced, Large-Scale, Long-Tailed Dataset For Anime Character Recognition
• Generating Gameplay-Relevant Art Assets with Transfer Learning
• Conditional Inference in Pre-trained Variational Autoencoders via Cross-coding
• A Neural Virtual Anchor Synthesizer based on Seq2Seq and GAN Models
• Universal Design Methodology for Printable Microstructural Materials via a New Deep Generative Learning Model: Application to a Piezocomposite
• How Old Are You? Face Age Translation with Identity Preservation Using GANs
• A Cyclically-Trained Adversarial Network for Invariant Representation Learning
• Level generation and style enhancement -- deep learning for game development overview
• Deep Animation Video Interpolation in the Wild
• Systematic Analysis and Removal of Circular Artifacts for StyleGAN
• Learning Diverse Stochastic Human-Action Generators by Learning Smooth Latent Transitions
• Segmentation and Generation of Magnetic Resonance Images by Deep Neural Networks
• Surrogate Gradient Field for Latent Space Manipulation
• Style-Restricted GAN: Multi-Modal Translation with Style Restriction Using Generative Adversarial Networks
• Improving Shape Deformation in Unsupervised Image-to-Image Translation