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

TL;DR

The ICDAR 2025 DIMT competition advances end-to-end document image translation research by evaluating models that jointly handle layout and text translation, with promising results from large-model approaches.

Contribution

This paper introduces a new challenge for end-to-end document image translation, including dataset, task definitions, and evaluation, fostering progress in multimodal document understanding.

Findings

Large models show promising translation quality for complex layouts.

The competition attracted diverse participation, indicating growing interest.

Opportunities for future research in multimodal document translation are highlighted.

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.