Saved in:
Bibliographic Details
Main Authors: Yu, Zhenyu, Idris, Mohd Yamani Idna, Wang, Hua, Wang, Pei, Qureshi, Rizwan, Raza, Shaina, Chadha, Aman, Xiang, Yong, Chen, Zhixiang
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2504.14108
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908558810939392
author Yu, Zhenyu
Idris, Mohd Yamani Idna
Wang, Hua
Wang, Pei
Qureshi, Rizwan
Raza, Shaina
Chadha, Aman
Xiang, Yong
Chen, Zhixiang
author_facet Yu, Zhenyu
Idris, Mohd Yamani Idna
Wang, Hua
Wang, Pei
Qureshi, Rizwan
Raza, Shaina
Chadha, Aman
Xiang, Yong
Chen, Zhixiang
contents We present DanceText, a training-free framework for multilingual text editing in images, designed to support complex geometric transformations and achieve seamless foreground-background integration. While diffusion-based generative models have shown promise in text-guided image synthesis, they often lack controllability and fail to preserve layout consistency under non-trivial manipulations such as rotation, translation, scaling, and warping. To address these limitations, DanceText introduces a layered editing strategy that separates text from the background, allowing geometric transformations to be performed in a modular and controllable manner. A depth-aware module is further proposed to align appearance and perspective between the transformed text and the reconstructed background, enhancing photorealism and spatial consistency. Importantly, DanceText adopts a fully training-free design by integrating pretrained modules, allowing flexible deployment without task-specific fine-tuning. Extensive experiments on the AnyWord-3M benchmark demonstrate that our method achieves superior performance in visual quality, especially under large-scale and complex transformation scenarios. Code is avaible at https://github.com/YuZhenyuLindy/DanceText.git.
format Preprint
id arxiv_https___arxiv_org_abs_2504_14108
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle DanceText: A Training-Free Layered Framework for Controllable Multilingual Text Transformation in Images
Yu, Zhenyu
Idris, Mohd Yamani Idna
Wang, Hua
Wang, Pei
Qureshi, Rizwan
Raza, Shaina
Chadha, Aman
Xiang, Yong
Chen, Zhixiang
Computer Vision and Pattern Recognition
We present DanceText, a training-free framework for multilingual text editing in images, designed to support complex geometric transformations and achieve seamless foreground-background integration. While diffusion-based generative models have shown promise in text-guided image synthesis, they often lack controllability and fail to preserve layout consistency under non-trivial manipulations such as rotation, translation, scaling, and warping. To address these limitations, DanceText introduces a layered editing strategy that separates text from the background, allowing geometric transformations to be performed in a modular and controllable manner. A depth-aware module is further proposed to align appearance and perspective between the transformed text and the reconstructed background, enhancing photorealism and spatial consistency. Importantly, DanceText adopts a fully training-free design by integrating pretrained modules, allowing flexible deployment without task-specific fine-tuning. Extensive experiments on the AnyWord-3M benchmark demonstrate that our method achieves superior performance in visual quality, especially under large-scale and complex transformation scenarios. Code is avaible at https://github.com/YuZhenyuLindy/DanceText.git.
title DanceText: A Training-Free Layered Framework for Controllable Multilingual Text Transformation in Images
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2504.14108