EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Style Transfer of Chinese Wuhu Iron Paintings Using Hierarchical Visual Transformer

Yuying Zhou, Yao Ren, Chao Wu, Minglong Xue

Sensors · 19.12.2024 · 24 (24) · 8103

DOI: 10.3390/s24248103 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 19.12.2024. Verfasst von Yuying Zhou und 3 weiteren Autor:innen. Beteiligte Einrichtung: Academy of Art and Design, Anhui University of Technology, Ma'anshan 243002, China. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 63 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: the Scientific Research Foundation for the Introduction of 425 Talent of Nanjing Institute of Industry Technology, the Scientific Research Foundation for the Introduction of Talent of Nanjing Institute of Industry Technology.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Within the domain of traditional art, Chinese Wuhu Iron Painting distinguishes itself through its distinctive craftsmanship, aesthetic expressiveness, and choice of materials, presenting a formidable challenge in the arena of stylistic transformation. This paper introduces an innovative Hierarchical Visual Transformer (HVT) framework aimed at achieving effectiveness and precision in the style transfer of Wuhu Iron Paintings. The study begins with an in-depth analysis of the artistic style of Wuhu Iron Paintings, extracting key stylistic elements that meet technical requirements for style conversion. Furthermore, in response to the unique artistic characteristics of Wuhu Iron Paintings, this research constructs a multi-layered network structure capable of effectively capturing and parsing style and content features. Building on this, we have designed an Efficient Local Attention Decoder (ELA-Decoder) that adaptively decodes the style and content features through correlation, significantly enhancing the length dependency of local and global information. Additionally, this paper proposes a Content Correction Module (CCM) to eliminate redundant features generated during the style transfer process, further optimizing the migration results. In light of the scarcity of existing datasets for Wuhu Iron Paintings, this study also collects and constructs a dedicated dataset for the style transfer of Wuhu Iron Paintings. Our method achieves optimal performance in terms of loss metrics, with a reduction of at least 4% in style loss and 5% in content loss compared to other advanced methods. Moreover, expert evaluations were conducted to validate the effectiveness of our approach, and the results show that our method received the highest number of votes, further demonstrating its superiority.

Schlagwörter

Stichwörter der Autor:innen

Chinese Wuhu iron paintingscontent correction modulefeature symmetrystyle transfer

Autor:innen und Institutionen

  • Academy of Art and Design, Anhui University of Technology, Ma'anshan 243002, China.
  • Engineeing Training Center, Nanjing Vocational University of Industry Technology, Nanjing 210023, China.
  • College of Computer Science and Engineering, Chongqing University of Technology, Chongqing 400054, China.

Förderung

  • the Scientific Research Foundation for the Introduction of 425 Talent of Nanjing Institute of Industry Technology
  • the Scientific Research Foundation for the Introduction of Talent of Nanjing Institute of Industry Technology

Zitieren

APA

Zhou, Y., Ren, Y., Wu, C., & Xue, M. (2024). Style Transfer of Chinese Wuhu Iron Paintings Using Hierarchical Visual Transformer. Sensors, 24(24), 8103. https://doi.org/10.3390/s24248103

Vancouver

Zhou Y, Ren Y, Wu C, Xue M. Style Transfer of Chinese Wuhu Iron Paintings Using Hierarchical Visual Transformer. Sensors. 2024;24(24):8103. doi:10.3390/s24248103

BibTeX
@article{Zhou2024,
  author = {Zhou, Yuying and Ren, Yao and Wu, Chao and Xue, Minglong},
  title = {Style Transfer of Chinese Wuhu Iron Paintings Using Hierarchical Visual Transformer},
  journal = {Sensors},
  year = {2024},
  volume = {24},
  number = {24},
  pages = {8103},
  doi = {10.3390/s24248103}
}
Kostenlos starten →