PATIMT-Bench: A Multi-Scenario Benchmark for Position-Aware Text Image Machine Translation in Large Vision-Language Models

• URL: http://arxiv.org/abs/2509.12278v1
• Date: Sun, 14 Sep 2025 08:33:23 GMT
• Title: PATIMT-Bench: A Multi-Scenario Benchmark for Position-Aware Text Image Machine Translation in Large Vision-Language Models
• Authors: Wanru Zhuang, Wenbo Li, Zhibin Lan, Xu Han, Peng Li, Jinsong Su,
• Abstract summary: Text Image Machine Translation (TIMT) aims to translate texts embedded within an image into another language.<n>We extend traditional TIMT into position-aware TIMT (PATIMT), aiming to support fine-grained and layout-preserving translation.<n>We construct the PATIMT benchmark (PATIMTBench), which consists of 10 diverse real-world scenarios.<n>Specifically, we introduce an Adaptive Image OCR Refinement Pipeline, which adaptively selects appropriate OCR tools based on scenario.
• Score: 32.38746546500033
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Text Image Machine Translation (TIMT) aims to translate texts embedded within an image into another language. Current TIMT studies primarily focus on providing translations for all the text within an image, while neglecting to provide bounding boxes and covering limited scenarios. In this work, we extend traditional TIMT into position-aware TIMT (PATIMT), aiming to support fine-grained and layoutpreserving translation, which holds great practical value but remains largely unexplored. This task comprises two key sub-tasks: regionspecific translation and full-image translation with grounding. To support existing models on PATIMT and conduct fair evaluation, we construct the PATIMT benchmark (PATIMTBench), which consists of 10 diverse real-world scenarios. Specifically, we introduce an Adaptive Image OCR Refinement Pipeline, which adaptively selects appropriate OCR tools based on scenario and refines the results of text-rich images. To ensure evaluation reliability, we further construct a test set, which contains 1,200 high-quality instances manually annotated and reviewed by human experts. After fine-tuning on our data, compact Large Vision-Language Models (LVLMs) achieve state-of-the-art performance on both sub-tasks. Experimental results also highlight the scalability and generalizability of our training data

Related papers

• PRIM: Towards Practical In-Image Multilingual Machine Translation [48.357528732061105]
  In-Image Machine Translation (IIMT) aims to translate images containing texts from one language to another.<n>Current research of end-to-end IIMT conducts on synthetic data, with simple background, single font, fixed text position, and bilingual translation.<n>We propose an end-to-end model VisTrans to handle the challenge of practical conditions in PRIM.
  arXiv  Detail & Related papers  (2025-09-05T14:38:07Z)
• Exploring In-Image Machine Translation with Real-World Background [5.839694459794486]
  In-Image Machine Translation aims to translate texts within images from one language to another.<n>We propose the DebackX model, which separates the background and text-image from the source image.<n> Experimental results show that our model achieves improvements in both translation quality and visual effect.
  arXiv  Detail & Related papers  (2025-05-21T09:02:53Z)
• AnyTrans: Translate AnyText in the Image with Large Scale Models [88.5887934499388]
  This paper introduces AnyTrans, an all-encompassing framework for the task-Translate AnyText in the Image (TATI) Our framework incorporates contextual cues from both textual and visual elements during translation. We have meticulously compiled a test dataset called MTIT6, which consists of multilingual text image translation data from six language pairs.
  arXiv  Detail & Related papers  (2024-06-17T11:37:48Z)
• Advancing Visual Grounding with Scene Knowledge: Benchmark and Method [74.72663425217522]
  Visual grounding (VG) aims to establish fine-grained alignment between vision and language. Most existing VG datasets are constructed using simple description texts. We propose a novel benchmark of underlineScene underlineKnowledge-guided underlineVisual underlineGrounding.
  arXiv  Detail & Related papers  (2023-07-21T13:06:02Z)
• Exploring Better Text Image Translation with Multimodal Codebook [39.12169843196739]
  Text image translation (TIT) aims to translate the source texts embedded in the image to target translations. In this work, we first annotate a Chinese-English TIT dataset named OCRMT30K, providing convenience for subsequent studies. Then, we propose a TIT model with a multimodal codebook, which is able to associate the image with relevant texts. We present a multi-stage training framework involving text machine translation, image-text alignment, and TIT tasks, which fully exploits additional bilingual texts.
  arXiv  Detail & Related papers  (2023-05-27T08:41:18Z)
• Scene Graph as Pivoting: Inference-time Image-free Unsupervised Multimodal Machine Translation with Visual Scene Hallucination [88.74459704391214]
  In this work, we investigate a more realistic unsupervised multimodal machine translation (UMMT) setup. We represent the input images and texts with the visual and language scene graphs (SG), where such fine-grained vision-language features ensure a holistic understanding of the semantics. Several SG-pivoting based learning objectives are introduced for unsupervised translation training. Our method outperforms the best-performing baseline by significant BLEU scores on the task and setup.
  arXiv  Detail & Related papers  (2023-05-20T18:17:20Z)
• Beyond Triplet: Leveraging the Most Data for Multimodal Machine Translation [53.342921374639346]
  Multimodal machine translation aims to improve translation quality by incorporating information from other modalities, such as vision. Previous MMT systems mainly focus on better access and use of visual information and tend to validate their methods on image-related datasets. This paper establishes new methods and new datasets for MMT.
  arXiv  Detail & Related papers  (2022-12-20T15:02:38Z)
• Tackling Ambiguity with Images: Improved Multimodal Machine Translation and Contrastive Evaluation [72.6667341525552]
  We present a new MMT approach based on a strong text-only MT model, which uses neural adapters and a novel guided self-attention mechanism. We also introduce CoMMuTE, a Contrastive Multimodal Translation Evaluation set of ambiguous sentences and their possible translations. Our approach obtains competitive results compared to strong text-only models on standard English-to-French, English-to-German and English-to-Czech benchmarks.
  arXiv  Detail & Related papers  (2022-12-20T10:18:18Z)
• Improving End-to-End Text Image Translation From the Auxiliary Text Translation Task [26.046624228278528]
  We propose a novel text translation enhanced text image translation, which trains the end-to-end model with text translation as an auxiliary task. By sharing model parameters and multi-task training, our model is able to take full advantage of easily-available large-scale text parallel corpus.
  arXiv  Detail & Related papers  (2022-10-08T02:35:45Z)
• Unsupervised Vision-and-Language Pre-training via Retrieval-based Multi-Granular Alignment [66.77841319057299]
  We propose a novel unsupervised Vision-and-Language pre-training curriculum for non-parallel texts and images. We first construct a weakly aligned image-text corpus via a retrieval-based approach, then apply a set of multi-granular alignment pre-training tasks. A comprehensive ablation study shows each granularity is helpful to learn a stronger pre-trained model.
  arXiv  Detail & Related papers  (2022-03-01T05:34:01Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.