Skip to Main content Skip to Navigation
Conference papers

Deep Learning for Document Layout Generation: A First Reproducible Quantitative Evaluation and a Baseline Model

Abstract : Deep generative models have been recently experimented in automated document layout generation, which led to significant qualitative results, assessed through user studies and displayed visuals. However, no reproducible quantitative evaluation has been settled in these works, which prevents scientific comparison of upcoming models with previous models. In this context, we propose a fully reproducible evaluation method and an original and efficient baseline model. Our evaluation protocol is meticulously defined in this work, and backed with an open source code available on this link.
Complete list of metadata

https://hal.archives-ouvertes.fr/hal-03385806
Contributor : Nicolas Ragot Connect in order to contact the contributor
Submitted on : Tuesday, October 19, 2021 - 3:57:27 PM
Last modification on : Monday, October 25, 2021 - 9:03:39 AM

File

icdar.pdf
Files produced by the author(s)

Identifiers

Citation

Romain Carletto, Hubert Cardot, Nicolas Ragot. Deep Learning for Document Layout Generation: A First Reproducible Quantitative Evaluation and a Baseline Model. 16th International Conference on Document Analysis and Recognition 2021, Sep 2021, Lausanne, Switzerland. pp.20 - 35, ⟨10.1007/978-3-030-86334-0_2⟩. ⟨hal-03385806⟩

Share

Metrics

Record views

44

Files downloads

47