ArtStroke-GAN: A Unified Framework for Interpreting Watercolor Aesthetics via Personalized Stroke-Based Graphic Language

Painting is an expressive art form traditionally associated with considerable technical skill and prolonged training, making it largely inaccessible to the general public. Computational stroke-based rendering (SBR) approaches have emerged to simulate human-like artistic processes digitally; however,...

Full description

Saved in:
Bibliographic Details
Main Author: Laixi Zheng
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/11123435/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849228534551150592
author Laixi Zheng
author_facet Laixi Zheng
author_sort Laixi Zheng
collection DOAJ
description Painting is an expressive art form traditionally associated with considerable technical skill and prolonged training, making it largely inaccessible to the general public. Computational stroke-based rendering (SBR) approaches have emerged to simulate human-like artistic processes digitally; however, current methods encounter notable limitations, such as spatial inconsistencies, stylistic discontinuities, and insufficient control over fine-grained stroke details. To address these challenges, this paper introduces ArtStroke-GAN, a novel generative adversarial network framework designed to synthesize realistic and personalized watercolor paintings. The proposed framework employs a modular three-part GAN architecture consisting of a stroke-generation network, a dedicated color-enhancement module, and an adversarial discriminator. Adaptive spline-based stroke modeling and iterative, semantic-aware stroke optimization strategies are integrated, enabling progressive refinement from coarse to detailed artistic representations. Experimental evaluations conducted on diverse image datasets (CelebA and ImageNet) demonstrate that ArtStroke-GAN achieves superior performance compared to state-of-the-art methods, including Stroke-GAN, Paint Transformer, and Neural-Paint, across quantitative metrics such as LPIPS, FID, style loss, and content fidelity. Qualitative assessments further confirm its ability to produce aesthetically coherent, structurally consistent, and stylistically diverse watercolor renderings, significantly advancing the capability of computational art generation frameworks.
format Article
id doaj-art-b2725b0318124f8fb7088cc780e44b76
institution Kabale University
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-b2725b0318124f8fb7088cc780e44b762025-08-22T23:16:57ZengIEEEIEEE Access2169-35362025-01-011314495414497410.1109/ACCESS.2025.359818311123435ArtStroke-GAN: A Unified Framework for Interpreting Watercolor Aesthetics via Personalized Stroke-Based Graphic LanguageLaixi Zheng0https://orcid.org/0009-0004-5280-1296School of Painting and Drawing, Guangzhou Academy of Fine Arts, Guangzhou, ChinaPainting is an expressive art form traditionally associated with considerable technical skill and prolonged training, making it largely inaccessible to the general public. Computational stroke-based rendering (SBR) approaches have emerged to simulate human-like artistic processes digitally; however, current methods encounter notable limitations, such as spatial inconsistencies, stylistic discontinuities, and insufficient control over fine-grained stroke details. To address these challenges, this paper introduces ArtStroke-GAN, a novel generative adversarial network framework designed to synthesize realistic and personalized watercolor paintings. The proposed framework employs a modular three-part GAN architecture consisting of a stroke-generation network, a dedicated color-enhancement module, and an adversarial discriminator. Adaptive spline-based stroke modeling and iterative, semantic-aware stroke optimization strategies are integrated, enabling progressive refinement from coarse to detailed artistic representations. Experimental evaluations conducted on diverse image datasets (CelebA and ImageNet) demonstrate that ArtStroke-GAN achieves superior performance compared to state-of-the-art methods, including Stroke-GAN, Paint Transformer, and Neural-Paint, across quantitative metrics such as LPIPS, FID, style loss, and content fidelity. Qualitative assessments further confirm its ability to produce aesthetically coherent, structurally consistent, and stylistically diverse watercolor renderings, significantly advancing the capability of computational art generation frameworks.https://ieeexplore.ieee.org/document/11123435/Deep learninggenerative adversarial networksvisual aestheticsdigital paintingartistic image generation
spellingShingle Laixi Zheng
ArtStroke-GAN: A Unified Framework for Interpreting Watercolor Aesthetics via Personalized Stroke-Based Graphic Language
IEEE Access
Deep learning
generative adversarial networks
visual aesthetics
digital painting
artistic image generation
title ArtStroke-GAN: A Unified Framework for Interpreting Watercolor Aesthetics via Personalized Stroke-Based Graphic Language
title_full ArtStroke-GAN: A Unified Framework for Interpreting Watercolor Aesthetics via Personalized Stroke-Based Graphic Language
title_fullStr ArtStroke-GAN: A Unified Framework for Interpreting Watercolor Aesthetics via Personalized Stroke-Based Graphic Language
title_full_unstemmed ArtStroke-GAN: A Unified Framework for Interpreting Watercolor Aesthetics via Personalized Stroke-Based Graphic Language
title_short ArtStroke-GAN: A Unified Framework for Interpreting Watercolor Aesthetics via Personalized Stroke-Based Graphic Language
title_sort artstroke gan a unified framework for interpreting watercolor aesthetics via personalized stroke based graphic language
topic Deep learning
generative adversarial networks
visual aesthetics
digital painting
artistic image generation
url https://ieeexplore.ieee.org/document/11123435/
work_keys_str_mv AT laixizheng artstrokeganaunifiedframeworkforinterpretingwatercoloraestheticsviapersonalizedstrokebasedgraphiclanguage