EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

DALS: Diffusion-Based Artistic Landscape Sketch

Junho Kim, Heekyung Yang, Kyungha Min

Mathematics · 11.01.2024 · 12 (2) · 238

DOI: 10.3390/math12020238 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Mathematics, online erschienen am 11.01.2024. Verfasst von Junho Kim und 2 weiteren Autor:innen. Die Arbeit wurde bisher 12-mal zitiert (Crossref) und nennt 49 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Sangmyung University.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

We propose a framework that synthesizes artistic landscape sketches using a diffusion model-based approach. Furthermore, we suggest a three-channel perspective map (3CPM) that mimics the artistic skill used by real artists. We employ Stable Diffusion, which leads us to use ControlNet to process 3CPM in Stable Diffusion. Additionally, we adopt the Low Rank Adaptation (LoRA) method to fine-tune our framework, thereby enhancing the quality of sketch and resolving the color-remaining problem, which is a frequently observed artifact in the sketch images using diffusion models. We implement a bimodal sketch generation interface: text to sketch and image to sketch. In producing a sketch, a guide token is used so that our method synthesizes an artistic sketch in both cases. Finally, we evaluate our framework using quantitative and quantitative schemes. Various sketch images synthesized by our framework demonstrate the excellence of our study.

Förderung

  • Sangmyung University

Zitieren

APA

Kim, J., Yang, H., & Min, K. (2024). DALS: Diffusion-Based Artistic Landscape Sketch. Mathematics, 12(2), 238. https://doi.org/10.3390/math12020238

Vancouver

Kim J, Yang H, Min K. DALS: Diffusion-Based Artistic Landscape Sketch. Mathematics. 2024;12(2):238. doi:10.3390/math12020238

BibTeX
@article{Kim2024,
  author = {Kim, Junho and Yang, Heekyung and Min, Kyungha},
  title = {DALS: Diffusion-Based Artistic Landscape Sketch},
  journal = {Mathematics},
  year = {2024},
  volume = {12},
  number = {2},
  pages = {238},
  doi = {10.3390/math12020238}
}
Kostenlos starten →