Advanced Layout Analysis Models for Docling
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866912587556323328 |
|---|---|
| author | Livathinos, Nikolaos Auer, Christoph Nassar, Ahmed de Lima, Rafael Teixeira Lysak, Maksym Ebouky, Brown Berrospi, Cesar Dolfi, Michele Vagenas, Panagiotis Omenetti, Matteo Dinkla, Kasper Kim, Yusik Weber, Valery Morin, Lucas Meijer, Ingmar Kuropiatnyk, Viktor Strohmeyer, Tim Gurbuz, A. Said Staar, Peter W. J. |
| author_facet | Livathinos, Nikolaos Auer, Christoph Nassar, Ahmed de Lima, Rafael Teixeira Lysak, Maksym Ebouky, Brown Berrospi, Cesar Dolfi, Michele Vagenas, Panagiotis Omenetti, Matteo Dinkla, Kasper Kim, Yusik Weber, Valery Morin, Lucas Meijer, Ingmar Kuropiatnyk, Viktor Strohmeyer, Tim Gurbuz, A. Said Staar, Peter W. J. |
| contents | This technical report documents the development of novel Layout Analysis models integrated into the Docling document-conversion pipeline. We trained several state-of-the-art object detectors based on the RT-DETR, RT-DETRv2 and DFINE architectures on a heterogeneous corpus of 150,000 documents (both openly available and proprietary). Post-processing steps were applied to the raw detections to make them more applicable to the document conversion task. We evaluated the effectiveness of the layout analysis on various document benchmarks using different methodologies while also measuring the runtime performance across different environments (CPU, Nvidia and Apple GPUs). We introduce five new document layout models achieving 20.6% - 23.9% mAP improvement over Docling's previous baseline, with comparable or better runtime. Our best model, "heron-101", attains 78% mAP with 28 ms/image inference time on a single NVIDIA A100 GPU. Extensive quantitative and qualitative experiments establish best practices for training, evaluating, and deploying document-layout detectors, providing actionable guidance for the document conversion community. All trained checkpoints, code, and documentation are released under a permissive license on HuggingFace. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_11720 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Advanced Layout Analysis Models for Docling Livathinos, Nikolaos Auer, Christoph Nassar, Ahmed de Lima, Rafael Teixeira Lysak, Maksym Ebouky, Brown Berrospi, Cesar Dolfi, Michele Vagenas, Panagiotis Omenetti, Matteo Dinkla, Kasper Kim, Yusik Weber, Valery Morin, Lucas Meijer, Ingmar Kuropiatnyk, Viktor Strohmeyer, Tim Gurbuz, A. Said Staar, Peter W. J. Computer Vision and Pattern Recognition This technical report documents the development of novel Layout Analysis models integrated into the Docling document-conversion pipeline. We trained several state-of-the-art object detectors based on the RT-DETR, RT-DETRv2 and DFINE architectures on a heterogeneous corpus of 150,000 documents (both openly available and proprietary). Post-processing steps were applied to the raw detections to make them more applicable to the document conversion task. We evaluated the effectiveness of the layout analysis on various document benchmarks using different methodologies while also measuring the runtime performance across different environments (CPU, Nvidia and Apple GPUs). We introduce five new document layout models achieving 20.6% - 23.9% mAP improvement over Docling's previous baseline, with comparable or better runtime. Our best model, "heron-101", attains 78% mAP with 28 ms/image inference time on a single NVIDIA A100 GPU. Extensive quantitative and qualitative experiments establish best practices for training, evaluating, and deploying document-layout detectors, providing actionable guidance for the document conversion community. All trained checkpoints, code, and documentation are released under a permissive license on HuggingFace. |
| title | Advanced Layout Analysis Models for Docling |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2509.11720 |