CAMS: Color-Aware Multi-Style Transfer
Mahmoud Afifi, Abdullah Abuolaim, Mostafa Hussien, Marcus A. Brubaker,, Michael S. Brown

TL;DR
CAMS introduces a color-aware multi-style transfer method that preserves style-color correlations, allowing for more flexible and visually appealing style transfer results, especially with images exhibiting multiple styles.
Contribution
It proposes a simple modification to Gram matrix-based style transfer to incorporate color-awareness and user-controlled style-color associations.
Findings
Produces aesthetically pleasing results with multiple styles
Enables user control over style-color relationships
Outperforms prior methods in preserving style-color correlations
Abstract
Image style transfer aims to manipulate the appearance of a source image, or "content" image, to share similar texture and colors of a target "style" image. Ideally, the style transfer manipulation should also preserve the semantic content of the source image. A commonly used approach to assist in transferring styles is based on Gram matrix optimization. One problem of Gram matrix-based optimization is that it does not consider the correlation between colors and their styles. Specifically, certain textures or structures should be associated with specific colors. This is particularly challenging when the target style image exhibits multiple style types. In this work, we propose a color-aware multi-style transfer method that generates aesthetically pleasing results while preserving the style-color correlation between style and generated images. We achieve this desired outcome by…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsImage Enhancement Techniques · Advanced Image Processing Techniques · Advanced Vision and Imaging
