---
title: "FlowTranslator: Training-Free In-Image Machine Translation with Flow-Based Editing"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2611.04303v1"
permalink: "https://feed.astralor.com/items/itm_fd5bfe86911c235704b74c57"
published: "2026-11-03T04:33:47.000Z"
score: 59
channel: "tech"
tags: ["LLM","推理效率","RAG","FlowTranslator","Training-Free In-Image Machine","Translation","Flow-Based Editing In-image","IIMT"]
---

# FlowTranslator: Training-Free In-Image Machine Translation with Flow-Based Editing

## At a glance

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…

## Key points

- 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.

## Full text

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.

---

Verify against the original before citing; curated by Astral Feed: https://feed.astralor.com/items/itm_fd5bfe86911c235704b74c57