AesStyler: Aesthetic guided universal style transfer

Yi, Ran, Zhu, Haokun, Hu, Teng, Lai, Yukun ORCID: https://orcid.org/0000-0002-2094-5680 and Rosin, Paul ORCID: https://orcid.org/0000-0002-4965-3884 2024. AesStyler: Aesthetic guided universal style transfer. Presented at: ACM Multimedia 2024, Melbourne, Australia, 28 October - 1 November 2024. MM '24: Proceedings of the 32nd ACM International Conference on Multimedia. ACM, pp. 9789-9798. 10.1145/3664647.3680784

Preview

PDF - Accepted Post-Print Version Download (12MB) | Preview

Abstract

Recent studies have shown impressive progress in universal style transfer which can integrate arbitrary styles into content images. However, existing approaches struggle with low aesthetics and disharmonious patterns in the final results. To address this problem, we propose AesStyler, a novel Aesthetic Guided Universal Style Transfer method. Specifically, our approach introduces the aesthetic assessment model, trained on a dataset with human-assessed aesthetic scores, into the universal style transfer task to accurately capture aesthetic features that universally resonate with human aesthetic preferences. Unlike previous methods which only consider aesthetics of specific style images, we propose to build a Universal Aesthetic Codebook (UAC) to harness universal aesthetic features that encapsulate the global aspects of aesthetics. Aesthetic features are fed into a novel Universal and Style-specific Aesthetic-Guided Attention (USAesA) module to guide the style transfer process. USAesA empowers our model to integrate the aesthetic attributes of both universal and style-specific aesthetic features with style features and facilitates the fusion of these aesthetically enhanced style features with content features. Extensive experiments and user studies have demonstrated that our approach generates aesthetically more harmonious and pleasing results than the state-ofthe- art methods, both aesthetic-free and aesthetic-aware. The code is available at: https://github.com/zwandering/AesStyler.

Item Type:	Conference or Workshop Item (Paper)
Date Type:	Published Online
Status:	Published
Schools:	Computer Science & Informatics
Publisher:	ACM
Date of First Compliant Deposit:	7 September 2024
Date of Acceptance:	15 July 2024
Last Modified:	15 Nov 2024 10:22
URI:	https://orca.cardiff.ac.uk/id/eprint/171915

Actions (repository staff only)

Edit Item