Customizable pattern synthesis: a deep generative approach for lantern designs
Pattern design is essential in various domains, especially in traditional lantern production, where patterns convey cultural history and artistic values. Our research presents an innovative generative model that produces customizable lantern patterns, integrating classical aesthetics with modern des...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
PeerJ Inc.
2025-03-01
|
| Series: | PeerJ Computer Science |
| Subjects: | |
| Online Access: | https://peerj.com/articles/cs-2732.pdf |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850251877682249728 |
|---|---|
| author | Mengran Yan Chun Tang Jida Yan Siti Suhaily Surip |
| author_facet | Mengran Yan Chun Tang Jida Yan Siti Suhaily Surip |
| author_sort | Mengran Yan |
| collection | DOAJ |
| description | Pattern design is essential in various domains, especially in traditional lantern production, where patterns convey cultural history and artistic values. Our research presents an innovative generative model that produces customizable lantern patterns, integrating classical aesthetics with modern design features via a generative adversarial network (GAN)-based framework. The model was trained on an extensive dataset of over 17,000 pattern images over ten various categories. Experimental assessment demonstrates the model’s remarkable proficiency, achieving an Inception Score of 5.259, much surpassing the performance of other GAN-based approaches. This exceptional result demonstrates the effective integration of traditional pattern elements with AI-driven design processes. The model offers enhanced design flexibility via noise vector hybridization and post-processing techniques, allowing for accurate control over pattern production while preserving cultural authenticity. These capabilities make our model a valuable tool for modernizing lantern pattern design while maintaining classic artistic elements. |
| format | Article |
| id | doaj-art-2961d5eb29a940e2bfb36a2c7faf9203 |
| institution | OA Journals |
| issn | 2376-5992 |
| language | English |
| publishDate | 2025-03-01 |
| publisher | PeerJ Inc. |
| record_format | Article |
| series | PeerJ Computer Science |
| spelling | doaj-art-2961d5eb29a940e2bfb36a2c7faf92032025-08-20T01:57:48ZengPeerJ Inc.PeerJ Computer Science2376-59922025-03-0111e273210.7717/peerj-cs.2732Customizable pattern synthesis: a deep generative approach for lantern designsMengran Yan0Chun Tang1Jida Yan2Siti Suhaily Surip3Fine Arts Department, Bozhou University, Bozhou City, Anhui Province, ChinaFine Arts Department, Bozhou University, Bozhou City, Anhui Province, ChinaInternational Education Institute, Quanzhou University of Information Engineering, Quanzhou City, Fujian Province, ChinaProduct Design Department, School of The Arts, Universiti Sains Malaysia, Penang, MalaysiaPattern design is essential in various domains, especially in traditional lantern production, where patterns convey cultural history and artistic values. Our research presents an innovative generative model that produces customizable lantern patterns, integrating classical aesthetics with modern design features via a generative adversarial network (GAN)-based framework. The model was trained on an extensive dataset of over 17,000 pattern images over ten various categories. Experimental assessment demonstrates the model’s remarkable proficiency, achieving an Inception Score of 5.259, much surpassing the performance of other GAN-based approaches. This exceptional result demonstrates the effective integration of traditional pattern elements with AI-driven design processes. The model offers enhanced design flexibility via noise vector hybridization and post-processing techniques, allowing for accurate control over pattern production while preserving cultural authenticity. These capabilities make our model a valuable tool for modernizing lantern pattern design while maintaining classic artistic elements.https://peerj.com/articles/cs-2732.pdfLantern patternsDeep learningGenerative modelPattern synthesis |
| spellingShingle | Mengran Yan Chun Tang Jida Yan Siti Suhaily Surip Customizable pattern synthesis: a deep generative approach for lantern designs PeerJ Computer Science Lantern patterns Deep learning Generative model Pattern synthesis |
| title | Customizable pattern synthesis: a deep generative approach for lantern designs |
| title_full | Customizable pattern synthesis: a deep generative approach for lantern designs |
| title_fullStr | Customizable pattern synthesis: a deep generative approach for lantern designs |
| title_full_unstemmed | Customizable pattern synthesis: a deep generative approach for lantern designs |
| title_short | Customizable pattern synthesis: a deep generative approach for lantern designs |
| title_sort | customizable pattern synthesis a deep generative approach for lantern designs |
| topic | Lantern patterns Deep learning Generative model Pattern synthesis |
| url | https://peerj.com/articles/cs-2732.pdf |
| work_keys_str_mv | AT mengranyan customizablepatternsynthesisadeepgenerativeapproachforlanterndesigns AT chuntang customizablepatternsynthesisadeepgenerativeapproachforlanterndesigns AT jidayan customizablepatternsynthesisadeepgenerativeapproachforlanterndesigns AT sitisuhailysurip customizablepatternsynthesisadeepgenerativeapproachforlanterndesigns |