What is it about?
The objective of arbitrary style transfer is to apply a given artistic or photo-realistic style to a target image.
Featured Image
Why is it important?
Although current methods have shown some success in transferring style, arbitrary style transfer still has several issues, including content leakage. Embedding an artistic style can result in unintended changes to the image content. This paper proposes an iterative framework called Restorable Arbitrary Style Transfer (RAST) to efectively ensure content preservation and mitigate potential alterations to the content information. RAST can transmit both content and style information through multi-restorations and balance the content-style trade-of in stylized images using the image restoration accuracy.
Perspectives
To ensure RAST’s efectiveness, we introduce two novel loss functions: multi-restoration loss and style diference loss. We also propose a new quantitative evaluation method to assess content preservation and style embedding performance. Experimental results show that RAST outperforms state-of-the-art methods in generating stylized images that preserve content and embed style accurately.
Yingnan Ma
University of Alberta
Read the Original
This page is a summary of: RAST: Restorable Arbitrary Style Transfer, ACM Transactions on Multimedia Computing Communications and Applications, December 2023, ACM (Association for Computing Machinery),
DOI: 10.1145/3638770.
You can read the full text:
Contributors
The following have contributed to this page
