Saved in:
Bibliographic Details
Main Authors: Hamdi, Laziz, Tamasna, Amine, Boisson, Pascal, Paquet, Thierry
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2605.22422
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910245946654720
author Hamdi, Laziz
Tamasna, Amine
Boisson, Pascal
Paquet, Thierry
author_facet Hamdi, Laziz
Tamasna, Amine
Boisson, Pascal
Paquet, Thierry
contents Table structure recognition (TSR) requires both table-level coherence (row/column counts, headers, spanning cells) and precise separator localization. We introduce FastTab, a grid-centric TSR model that avoids autoregressive HTML decoding by combining (i) a lightweight Tiny Recursive Module (TRM) for global reasoning and (ii) axial 1D Transformer encoders that capture long-range dependencies along rows and columns. The model predicts row/column counts, header rows, and separators to construct a grid, then infers rowspan/colspan using ROI-aligned cell features. Across four benchmarks (PubTabNet, FinTabNet, PubTables-1M, and SciTSR), FastTab achieves competitive structure recovery performance while operating at low-latency inference. We further study robustness under pixel-level anonymisation and show an extension to curved separators for camera-captured documents. The source code will be made publicly available at https://github.com/hamdilaziz/FastTab .
format Preprint
id arxiv_https___arxiv_org_abs_2605_22422
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle FastTab: A Fast Table Recognizer with a Tiny Recursive Module and 1D Transformers
Hamdi, Laziz
Tamasna, Amine
Boisson, Pascal
Paquet, Thierry
Computer Vision and Pattern Recognition
Artificial Intelligence
Table structure recognition (TSR) requires both table-level coherence (row/column counts, headers, spanning cells) and precise separator localization. We introduce FastTab, a grid-centric TSR model that avoids autoregressive HTML decoding by combining (i) a lightweight Tiny Recursive Module (TRM) for global reasoning and (ii) axial 1D Transformer encoders that capture long-range dependencies along rows and columns. The model predicts row/column counts, header rows, and separators to construct a grid, then infers rowspan/colspan using ROI-aligned cell features. Across four benchmarks (PubTabNet, FinTabNet, PubTables-1M, and SciTSR), FastTab achieves competitive structure recovery performance while operating at low-latency inference. We further study robustness under pixel-level anonymisation and show an extension to curved separators for camera-captured documents. The source code will be made publicly available at https://github.com/hamdilaziz/FastTab .
title FastTab: A Fast Table Recognizer with a Tiny Recursive Module and 1D Transformers
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2605.22422