Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

ICDAR 2025 Competition on End-to-End Document Image Machine Translation Towards Complex Layouts

Yaping Zhang, Yupu Liang, Zhiyang Zhang, Zhiyuan Chen, Lu Xiang, Yang Zhao, Yu Zhou, Chengqing Zong

TL;DR

Analysis shows that large-model approaches establish a promising new paradigm for translating complex-layout document images and highlight substantial opportunities for future research in the DIMT 2025 Challenge.

Abstract

Document Image Machine Translation (DIMT) seeks to translate text embedded in document images from one language to another by jointly modeling both textual content and page layout, bridging optical character recognition (OCR) and natural language processing (NLP). The DIMT 2025 Challenge advances research on end-to-end document image translation, a rapidly evolving area within multimodal document understanding. The competition features two tracks, OCR-free and OCR-based, each with two subtasks for small (less than 1B parameters) and large (greater than 1B parameters) models. Participants submit a single unified DIMT system, with the option to incorporate provided OCR transcripts. Running from December 10, 2024 to April 20, 2025, the competition attracted 69 teams and 27 valid submissions in total. Track 1 had 34 teams and 13 valid submissions, while Track 2 had 35 teams and 14 valid submissions. In this report, we present the challenge motivation, dataset construction, task definitions, evaluation protocol, and a summary of results. Our analysis shows that large-model approaches establish a promising new paradigm for translating complex-layout document images and highlight substantial opportunities for future research.

ICDAR 2025 Competition on End-to-End Document Image Machine Translation Towards Complex Layouts

TL;DR

Analysis shows that large-model approaches establish a promising new paradigm for translating complex-layout document images and highlight substantial opportunities for future research in the DIMT 2025 Challenge.

Abstract

Document Image Machine Translation (DIMT) seeks to translate text embedded in document images from one language to another by jointly modeling both textual content and page layout, bridging optical character recognition (OCR) and natural language processing (NLP). The DIMT 2025 Challenge advances research on end-to-end document image translation, a rapidly evolving area within multimodal document understanding. The competition features two tracks, OCR-free and OCR-based, each with two subtasks for small (less than 1B parameters) and large (greater than 1B parameters) models. Participants submit a single unified DIMT system, with the option to incorporate provided OCR transcripts. Running from December 10, 2024 to April 20, 2025, the competition attracted 69 teams and 27 valid submissions in total. Track 1 had 34 teams and 13 valid submissions, while Track 2 had 35 teams and 14 valid submissions. In this report, we present the challenge motivation, dataset construction, task definitions, evaluation protocol, and a summary of results. Our analysis shows that large-model approaches establish a promising new paradigm for translating complex-layout document images and highlight substantial opportunities for future research.
Paper Structure (18 sections, 3 figures, 8 tables)

This paper contains 18 sections, 3 figures, 8 tables.

Table of Contents

  1. Introduction
  2. Related Works
  3. Benchmark Description
  4. Organization
  5. Track 1. OCR-based DIMT
  6. Track 2. OCR-free DIMT
  7. Dataset
  8. Evaluation Protocol
  9. Submissions and Results
  10. Track 1.1 OCR-based DIMT-LLM
  11. Track 1.2 OCR-based DIMT-Small
  12. Track 2.1 OCR-free DIMT-LLM
  13. Track 2.2 OCR-free DIMT-Small
  14. Discussion
  15. Participation Trends and Performance Gap
  16. ...and 3 more sections

Figures (3)

  • Figure 1: Document image examples of the DIMT 2025 challenge. (a)(b): Web document examples in Track 1; (c)(d): arXiv document examples in Track 2.
  • Figure 2: An example of input and output for Track 1 is shown in (a). The purple rectangular box highlights the text areas that need to be reordered and translated, with the words and their corresponding bounding boxes (indicated by the red boxes) serving as the model's input. For clarity, only the area within the rectangular box is illustrated, but in practice, the entire page is considered. (b) The results of reordering and translating the text in the rectangular box area.
  • Figure 3: An input and output example of Track 2. (a) is the original document image. (b) is the translated text in markdown format after rendering. The blocks with the same color represent the corresponding original text and translated text.