LEAST: "Local" text-conditioned image style transfer

TL;DR

This paper introduces LEAST, a novel end-to-end pipeline for localized text-conditioned image style transfer that effectively aligns with user intent, overcoming limitations of existing methods in localizing style transfer without distorting content.

Contribution

The paper presents a new end-to-end approach for local style transfer guided by text prompts, addressing the challenge of localized stylization while preserving image content.

Findings

Current methods struggle with localized style transfer.

LEAST effectively localizes style transfer to specific regions.

Quantitative and qualitative results validate LEAST's effectiveness.

Abstract

Text-conditioned style transfer enables users to communicate their desired artistic styles through text descriptions, offering a new and expressive means of achieving stylization. In this work, we evaluate the text-conditioned image editing and style transfer techniques on their fine-grained understanding of user prompts for precise "local" style transfer. We find that current methods fail to accomplish localized style transfers effectively, either failing to localize style transfer to certain regions in the image, or distorting the content and structure of the input image. To this end, we develop an end-to-end pipeline for "local" style transfer tailored to align with users' intent. Further, we substantiate the effectiveness of our approach through quantitative and qualitative analysis. The project code is available at: https://github.com/silky1708/local-style-transfer.