Towards the Automatic Anime Characters Creation with Generative Adversarial Networks

By Yanghua Jin, Jiakai Zhang, Minjun Li, Yingtao Tian, Huachun Zhu, Zhihao Fang. 2017

202 citations recorded by the source corpus.

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 (this http URL) with our pre-trained model available online, which makes the model easily accessible to general public.

Subfields: Computer Vision and Pattern Recognition, Control and Systems Engineering

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Control and Systems Engineering

Citations in the corpus

Black-Box vs. White-Box: Understanding Their Advantages and Weaknesses From a Practical Point of View (2019, background): “large number of interesting applications of GANs [37], such as generating examples for image datasets [36], [38], creating photographs of human faces, objects, and scenes [39]–[41], generating cartoon and Pokemon characters [42], imageto-image translation [43], [44], text-to-image translation [45]–[”
Unsupervised Discovery of Disentangled Manifolds in GANs (2020, background): “Anime Faces and SNGAN this dataset[22] includes 63632 high-quality anime faces images.”
Bailando: 3D Dance Generation by Actor-Critic GPT with Choreographic Memory (2022, methodology): “The music features are extracted by the public audio processing toolbox Librosa [17], including mel frequency cepstral co-efﬁcients (MFCC) , MFCC delta , constant-Q chromagram , tempogram and onset strength , which are 438 -dim in total, and are mapped to the same dimension of GPT via a learned line”
A Survey on Generative Adversarial Networks: Variants, Applications, and Training (2020, methodology): “Anime characters generation: Anime character with GAN [35], PS-GAN [39]”
Artificial intelligence in the creative industries: a review (2020, background): “new examples of bedrooms [19], cartoon characters [21], celebrity headshots [26].”
Applications of Generative Adversarial Networks (GANs): An Updated Review (2019, methodology): “GAN can auto-generate and colorize Anime characters [49].”
Demystifying MMD GANs (2018, background): “ plausible samples, as illustrated particularly directly by Danihelka et al. (2017). This class of models has recently led to many impressive examples of image generation (e.g. Huang et al., 2017a;b; Jin et al., 2017; Zhu et al., 2017). GANs are, however, notoriously tricky to train (Salimans et al.”