# Controllable Segmentation-Based Text-Guided Style Editing

Source: [Controllable Segmentation-Based Text-Guided Style Editing](<https://www.sota2.com/research/paper/68fa7a441e209131cea820e3>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T05:16:12.275Z

Authors: Jingwen Li, Aravind Chandrasekar, Mariana Rocha, Chao Li, Yuqing Chen

Published: 2025-03-20T13:24:41.000Z

## Abstract

We present a novel approach for controllable, region-specific style editing driven by textual prompts. Building upon the state-space style alignment framework introduced by \\emph{StyleMamba}, our method integrates a semantic segmentation model into the style transfer pipeline. This allows users to selectively apply text-driven style changes to specific segments (e.g., \`\`turn the building into a cyberpunk tower'') while leaving other regions (e.g., \`\`people'' or \`\`trees'') unchanged. By incorporating region-wise condition vectors and a region-specific directional loss, our method achieves high-fidelity transformations that respect both semantic boundaries and user-driven style descriptions. Extensive experiments demonstrate that our approach can flexibly handle complex scene stylizations in real-world scenarios, improving control and quality over purely global style transfer methods.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2503.16129>)

[PDF](<https://arxiv.org/pdf/2503.16129.pdf>)