AnimeGAN: A Novel Lightweight GAN for Photo Animation

Chen, Jie; Liu, Gang; Chen, Xin

doi:10.1007/978-981-15-5577-0_18

Cited by 62 publications

(45 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Kim et al [6] proposed the AdaLIN process, in which parameters can be trained by adaptively selecting the ratio between the instance and layer normalization processes, thus making it possible to construct robust translation models capable of handling tasks that require large shape gap changes, such as selfie-to-anime translations. New architectures have also been developed [7,18] that utilize a pretrained VGG19 [10] to calculate the content loss.…”

Section: One-to-one Domain Translationmentioning

confidence: 99%

Multi-CartoonGAN with Conditional Adaptive Instance-Layer Normalization for Conditional Artistic Face Translation

Komatsu

Gonsalves

2022

View full text Add to dashboard Cite

In CycleGAN, an image-to-image translation architecture was established without the use of paired datasets by employing both adversarial and cycle consistency loss. The success of CycleGAN was followed by numerous studies that proposed new translation models. For example, StarGAN works as a multi-domain translation model based on a single generator–discriminator pair, while U-GAT-IT aims to close the large face-to-anime translation gap by adapting its original normalization to the process. However, constructing robust and conditional translation models requires tradeoffs when the computational costs of training on graphic processing units (GPUs) are considered. This is because, if designers attempt to implement conditional models with complex convolutional neural network (CNN) layers and normalization functions, the GPUs will need to secure large amounts of memory when the model begins training. This study aims to resolve this tradeoff issue via the development of Multi-CartoonGAN, which is an improved CartoonGAN architecture that can output conditional translated images and adapt to large feature gap translations between the source and target domains. To accomplish this, Multi-CartoonGAN reduces the computational cost by using a pretrained VGGNet to calculate the consistency loss instead of reusing the generator. Additionally, we report on the development of the conditional adaptive layer-instance normalization (CAdaLIN) process for use with our model to make it robust to unique feature translations. We performed extensive experiments using Multi-CartoonGAN to translate real-world face images into three different artistic styles: portrait, anime, and caricature. An analysis of the visualized translated images and GPU computation comparison shows that our model is capable of performing translations with unique style features that follow the conditional inputs and at a reduced GPU computational cost during training.

show abstract

Section: One-to-one Domain Translationmentioning

confidence: 99%

Multi-CartoonGAN with Conditional Adaptive Instance-Layer Normalization for Conditional Artistic Face Translation

Komatsu

Gonsalves

2022

View full text Add to dashboard Cite

show abstract

“…GANs are a specialized class of deep generative models that learn to generate novel data samples from random noise, while matching a given data distribution [12]. For instance, a GAN trained on a dataset of anime character images can generate novel anime characters, which look highly authentic, at least superficially [4]. Their flexibility and a wide-range of applications make GANs a popular choice for generation.…”

Section: Deep Learningmentioning

confidence: 99%

“…We use Precision, Recall, and F1-Score to evaluate performance of different architectures described above. Table 2 compiles the results of our hate speech experiments 4 . It includes information about input modalities involved, the experiment setting (binary/multi) and the type of fusion module used.…”

Section: Hate Speech Detectionmentioning

confidence: 99%

Towards A Multi-agent System for Online Hate Speech Detection

Sahu¹,

Cohen²,

Vechtomova³

2021

Preprint

View full text Add to dashboard Cite

This paper envisions a multi-agent system for detecting the presence of hate speech in online social media platforms such as Twitter and Facebook. We introduce a novel framework employing deep learning techniques to coordinate the channels of textual and image processing. Our experimental results aim to demonstrate the effectiveness of our methods for classifying online content, training the proposed neural network model to effectively detect hateful instances in the input. We conclude with a discussion of how our system may be of use to provide recommendations to users who are managing online social networks, showcasing the immense potential of intelligent multi-agent systems towards delivering social good 1 .

show abstract

“…For example, animation colorization has been widely studied [15,23,29] for practical applicatio; in this, the authors reduce the inputs of human labor and time for colorization. Furthermore, generative adversarial networks [16] promote the development of deep learning models for generative tasks in the anima-tion field, e.g., style transfer [8,9], image generation [20,40] and video interpolation [34]. We believe that AnimeCeleb is able to boost the research progress on various tasks in the animation domain.…”

Section: Related Workmentioning

confidence: 99%

AnimeCeleb: Large-Scale Animation CelebHeads Dataset for Head Reenactment

Kim¹,

Park²,

Lee³

et al. 2021

Preprint

View full text Add to dashboard Cite

Despite remarkable success in deep learning-based facerelated models, these models are still limited to the domain of real human faces. On the other hand, the domain of animation faces has been studied less intensively due to the absence of a well-organized dataset. In this paper, we present a large-scale animation celebfaces dataset (Anime-Celeb) via controllable synthetic animation models to boost research on the animation face domain. To facilitate the data generation process, we build a semi-automatic pipeline based on an open 3D software and a developed annotation system. This leads to constructing a large-scale animation face dataset that includes multi-pose and multi-style animation faces with rich annotations. Experiments suggest that our dataset is applicable to various animation-related tasks * These authors contributed equally. such as head reenactment and colorization.

show abstract

AnimeGAN: A Novel Lightweight GAN for Photo Animation

Cited by 62 publications

References 17 publications

Multi-CartoonGAN with Conditional Adaptive Instance-Layer Normalization for Conditional Artistic Face Translation

Multi-CartoonGAN with Conditional Adaptive Instance-Layer Normalization for Conditional Artistic Face Translation

Towards A Multi-agent System for Online Hate Speech Detection

AnimeCeleb: Large-Scale Animation CelebHeads Dataset for Head Reenactment

Contact Info

Product

Resources

About