EUVIMEDEUVIMED entdecken
Crossref

StyleShot: A Snapshot on Any Style

Junyao Gao, Yanan Sun, Yanchen Liu, Yinhao Tang, Yanhong Zeng, Ding Qi, Kai Chen, Cairong Zhao

IEEE Transactions on Pattern Analysis and Machine Intelligence · 2026-02 · 48 (2) · 1215-1228

DOI: 10.1109/tpami.2025.3610614 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2026-02. Verfasst von Junyao Gao und 7 weiteren Autor:innen. Die Arbeit wurde bisher 36-mal zitiert (Crossref) und nennt 78 Literaturangaben. Gefördert von: National Key R&D Program of China, National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Image Style Transfer aims to replicate the style of a reference image based on the content from a text description or another image. With the significant advancements in image generation through diffusion models, recent studies have attempted to either fine-tuning embeddings to learn the single style or utilizing the pre-trained CLIP image encoder to extract style representations. However, style-tuning requires substantial computational resources and the pre-trained CLIP image encoder is trained for semantic understanding rather than for style representation. To address these challenges, we introduce a style-aware encoder and a well-organized style dataset called StyleGallery to learn a good style representation that is crucial and sufficient for generalized style transfer without test-time tuning. With dedicated design for style learning, this style-aware encoder is trained to extract expressive style representation from multi-level patches with decoupling training strategy, and StyleGallery enables the generalization ability. Moreover, we employ a content extraction and content-fusion encoder to enhance image-driven style transfer. We highlight that, our approach, named StyleShot, is simple yet effective in mimicking various desired styles, i.e., 3D, flat, abstract or even fine-grained styles, without test-time tuning. Rigorous experiments validate that, StyleShot achieves superior performance across a wide range of styles compared to existing state-of-the-art text- and image-driven methods.

Förderung

  • National Key R&D Program of China
  • National Natural Science Foundation of China

Zitieren

APA

Gao, J., Sun, Y., Liu, Y., Tang, Y., Zeng, Y., Qi, D., Chen, K., & Zhao, C. (2026). StyleShot: A Snapshot on Any Style. IEEE Transactions on Pattern Analysis and Machine Intelligence, 48(2), 1215-1228. https://doi.org/10.1109/tpami.2025.3610614

Vancouver

Gao J, Sun Y, Liu Y, Tang Y, Zeng Y, Qi D, et al. StyleShot: A Snapshot on Any Style. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2026;48(2):1215-1228. doi:10.1109/tpami.2025.3610614

BibTeX
@article{Gao2026,
  author = {Gao, Junyao and Sun, Yanan and Liu, Yanchen and Tang, Yinhao and Zeng, Yanhong and Qi, Ding and Chen, Kai and Zhao, Cairong},
  title = {StyleShot: A Snapshot on Any Style},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year = {2026},
  volume = {48},
  number = {2},
  pages = {1215--1228},
  doi = {10.1109/tpami.2025.3610614}
}
Kostenlos starten →