An Attention-Based Generative Adversarial Network for Producing Illustrative Sketches

An illustrative sketch style expresses important shapes and regions of objects and scenes with salient lines and dark tones, while abstracting less important shapes and regions as vacant spaces. We present a framework that produces illustrative sketch styles from various photographs. Our framework i...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Jihyeon Yeom, Heekyung Yang, Kyungha Min
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	deep learning GAN attention map stylization illustrative sketch Mathematics QA1-939
Acceso en línea:	https://doaj.org/article/1073e24c3cd14971836f20cd34525cea
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:1073e24c3cd14971836f20cd34525cea
record_format	dspace
spelling	oai:doaj.org-article:1073e24c3cd14971836f20cd34525cea2021-11-11T18:19:43ZAn Attention-Based Generative Adversarial Network for Producing Illustrative Sketches10.3390/math92127912227-7390https://doaj.org/article/1073e24c3cd14971836f20cd34525cea2021-11-01T00:00:00Zhttps://www.mdpi.com/2227-7390/9/21/2791https://doaj.org/toc/2227-7390An illustrative sketch style expresses important shapes and regions of objects and scenes with salient lines and dark tones, while abstracting less important shapes and regions as vacant spaces. We present a framework that produces illustrative sketch styles from various photographs. Our framework is designed using a generative adversarial network (GAN), which comprised four modules: a style extraction module, a generator module, a discriminator module and RCCL module. We devise two key ideas to effectively extract illustrative sketch styles from sample artworks and to apply them to input photographs. The first idea is using an attention map that extracts the required style features from important shapes and regions of sample illustrative sketch styles. This attention map is used in the generator module of our framework for the effective production of illustrative sketch styles. The second idea is using a relaxed cycle consistency loss that evaluates the quality of the produced illustrative sketch styles by comparing images that are reconstructed from the produced illustrative sketch styles and the input photographs. This relaxed cycle consistency loss focuses on the comparison of important shapes and regions for an effective evaluation of the quality of the produced illustrative sketch styles. Our GAN-based framework with an attention map and a relaxed cycle consistency loss effectively produces illustrative sketch styles on various target photographs, including portraits, landscapes, and still lifes. We demonstrate the effectiveness of our framework through a human study, ablation study, and Frechet Inception Distance evaluation.Jihyeon YeomHeekyung YangKyungha MinMDPI AGarticledeep learningGANattention mapstylizationillustrative sketchMathematicsQA1-939ENMathematics, Vol 9, Iss 2791, p 2791 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	deep learning GAN attention map stylization illustrative sketch Mathematics QA1-939
spellingShingle	deep learning GAN attention map stylization illustrative sketch Mathematics QA1-939 Jihyeon Yeom Heekyung Yang Kyungha Min An Attention-Based Generative Adversarial Network for Producing Illustrative Sketches
description	An illustrative sketch style expresses important shapes and regions of objects and scenes with salient lines and dark tones, while abstracting less important shapes and regions as vacant spaces. We present a framework that produces illustrative sketch styles from various photographs. Our framework is designed using a generative adversarial network (GAN), which comprised four modules: a style extraction module, a generator module, a discriminator module and RCCL module. We devise two key ideas to effectively extract illustrative sketch styles from sample artworks and to apply them to input photographs. The first idea is using an attention map that extracts the required style features from important shapes and regions of sample illustrative sketch styles. This attention map is used in the generator module of our framework for the effective production of illustrative sketch styles. The second idea is using a relaxed cycle consistency loss that evaluates the quality of the produced illustrative sketch styles by comparing images that are reconstructed from the produced illustrative sketch styles and the input photographs. This relaxed cycle consistency loss focuses on the comparison of important shapes and regions for an effective evaluation of the quality of the produced illustrative sketch styles. Our GAN-based framework with an attention map and a relaxed cycle consistency loss effectively produces illustrative sketch styles on various target photographs, including portraits, landscapes, and still lifes. We demonstrate the effectiveness of our framework through a human study, ablation study, and Frechet Inception Distance evaluation.
format	article
author	Jihyeon Yeom Heekyung Yang Kyungha Min
author_facet	Jihyeon Yeom Heekyung Yang Kyungha Min
author_sort	Jihyeon Yeom
title	An Attention-Based Generative Adversarial Network for Producing Illustrative Sketches
title_short	An Attention-Based Generative Adversarial Network for Producing Illustrative Sketches
title_full	An Attention-Based Generative Adversarial Network for Producing Illustrative Sketches
title_fullStr	An Attention-Based Generative Adversarial Network for Producing Illustrative Sketches
title_full_unstemmed	An Attention-Based Generative Adversarial Network for Producing Illustrative Sketches
title_sort	attention-based generative adversarial network for producing illustrative sketches
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/1073e24c3cd14971836f20cd34525cea
work_keys_str_mv	AT jihyeonyeom anattentionbasedgenerativeadversarialnetworkforproducingillustrativesketches AT heekyungyang anattentionbasedgenerativeadversarialnetworkforproducingillustrativesketches AT kyunghamin anattentionbasedgenerativeadversarialnetworkforproducingillustrativesketches AT jihyeonyeom attentionbasedgenerativeadversarialnetworkforproducingillustrativesketches AT heekyungyang attentionbasedgenerativeadversarialnetworkforproducingillustrativesketches AT kyunghamin attentionbasedgenerativeadversarialnetworkforproducingillustrativesketches
_version_	1718431866186366976

An Attention-Based Generative Adversarial Network for Producing Illustrative Sketches

Ejemplares similares