Name Your Style: Text-Guided Artistic Style Transfer - Institut Polytechnique de Paris Access content directly
Conference Papers Year : 2023

Name Your Style: Text-Guided Artistic Style Transfer

Abstract

Image style transfer has attracted widespread attention in the past years. Despite its remarkable results, it requires additional style images available as references, making it less flexible and inconvenient. Using text is the most natural way to describe the style. Text can describe implicit abstract styles, like styles of specific artists or art movements. In this work, we propose a text-driven style transfer (TxST) that leverages advanced image-text encoders to control arbitrary style transfer. We introduce a contrastive training strategy to effectively extract style descriptions from the image-text model (i.e., CLIP), which aligns stylization with the text description. To this end, we also propose a novel cross-attention module to fuse style and content features. Finally, we achieve an arbitrary artist-aware style transfer to learn and transfer specific artistic characters such as Picasso, oil painting, or a rough sketch. Extensive experiments demonstrate that our approach outperforms the stateof-the-art methods. Moreover, it can mimic the styles of one or many artists to achieve attractive results, thus highlighting a promising future direction.
Fichier principal
Vignette du fichier
Liu_Name_Your_Style_Text-Guided_Artistic_Style_Transfer_CVPRW_2023_paper.pdf (7.16 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-04480544 , version 1 (27-02-2024)

Identifiers

  • HAL Id : hal-04480544 , version 1

Cite

Zhisong Liu, Li-Wen Wang, Wan-Chi Siu, Vicky Kalogeiton. Name Your Style: Text-Guided Artistic Style Transfer. Conference on Computer Vision and Pattern Recognition Workshop, Jun 2023, Vancouver, Canada. ⟨hal-04480544⟩
20 View
8 Download

Share

Gmail Facebook X LinkedIn More