Gatha: Relational Loss for Enhancing Text-Based Style Transfer

Surgan Jandial, Shripad V. Deshmukh, Abhinav Java, Simra Shahid, Balaji Krishnamurthy

CVPRW 2023 pp. 3546-3551

doi:10.1109/CVPRW59228.2023.00362 /cvprw/2023/jandial2023cvprw-gatha/

Abstract

Text-based style transfer is a promising area of research that enables the generation of stylistic images from plain text descriptions. However, the existing text-based style transfer techniques do not account for the subjective nature of prompt descriptions or the nuances of style-specific vocabulary during the optimization process. This severely limits the stylistic expression of the predominant models. In this paper, we address this gap by proposing Gatha, which incorporates subjectivity by introducing an additional loss function that enforces the relationship between stylized images and a proxy style set to be similar to the relationship between the text description and the proxy style set. We substantiate the effectiveness of Gatha through both qualitative and quantitative analysis against the existing state-of-the-art models and show that our approach allows for consistently improved stylized images.

CVPRW Semantic Scholar

Cite

Text

Jandial et al. "Gatha: Relational Loss for Enhancing Text-Based Style Transfer." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2023. doi:10.1109/CVPRW59228.2023.00362

Markdown

[Jandial et al. "Gatha: Relational Loss for Enhancing Text-Based Style Transfer." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2023.](https://mlanthology.org/cvprw/2023/jandial2023cvprw-gatha/) doi:10.1109/CVPRW59228.2023.00362

BibTeX

@inproceedings{jandial2023cvprw-gatha,
  title     = {{Gatha: Relational Loss for Enhancing Text-Based Style Transfer}},
  author    = {Jandial, Surgan and Deshmukh, Shripad V. and Java, Abhinav and Shahid, Simra and Krishnamurthy, Balaji},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
  year      = {2023},
  pages     = {3546-3551},
  doi       = {10.1109/CVPRW59228.2023.00362},
  url       = {https://mlanthology.org/cvprw/2023/jandial2023cvprw-gatha/}
}