| title | FlowTranslator: Training-Free In-Image Machine Translation with Flow-Based Editing |
|---|---|
| authors | Zhixian Li, Xingsong Ye, Yongkun Du, Yunyan Xiao, Yanglin Huang, Pinxuan Chen, Jiyu Zhuang, Cong Xu, Zhineng Chen |
| date | 2026-11-03 |
| venue | arXiv (preprint, not peer reviewed) |
| id | arXiv:2611.04303 |
| affiliation | Fudan University |
| upvotes | 10 (Hugging Face Daily Papers, 2026-11-05) |
| links | abs pdf hf |
| cite | |
| abstract | In-image machine translation (IIMT) replaces text in an image with its translation while preserving the surrounding visual context. Existing task-specific models achieve convincing performance but require massive paired training images before and after translation. As advanced text-to-image (T2I) models have reached a practically usable level of multilingual text generation, we argue that this capability can be transferred to IIMT and present FlowTranslator. It is a training-free IIMT framework that first employs an OCR model and an LLM to generate the translation prompt, which is injected into the T2I-based diffusion model. To optimize the accurate and natural generation of translated text, we introduce two trajectory controls: Region Coupling Release (RCR) partially decorrelates target-branch noise inside the text region early in the trajectory, while Coupling Expansion (CE) amplifies the emerging edit displacement mid-trajectory. Under the EasyOCR read-back protocol, FlowTranslator achieves average PRIM BLEU and COMET scores of 20.6 and 57.2, respectively, substantially outperforming the strong training-based baseline UniTranslator. On the more challenging and realistic whole-image ScenePair photographs translated into Chinese, it reaches 40.1\% exact-match accuracy and surpasses existing editing systems, some of which only address the text-rendering stage rather than the complete IIMT task. These results establish flow-based editing as a strong, fully training-free baseline for IIMT. |
bibtex
@misc{li2026flowtranslator,
title={FlowTranslator: Training-Free In-Image Machine Translation with Flow-Based Editing},
author={Zhixian Li and Xingsong Ye and Yongkun Du and Yunyan Xiao and Yanglin Huang and Pinxuan Chen and Jiyu Zhuang and Cong Xu and Zhineng Chen},
year={2026},
eprint={2611.04303},
archivePrefix={arXiv},
url={https://arxiv.org/abs/2611.04303}
}