Grab What You Need: Rethinking Complex Table Structure Recognition with Flexible Components Deliberation

TL;DR

This paper introduces GrabTab, a novel method for complex table structure recognition that leverages multiple components efficiently, outperforming existing methods especially in challenging scenarios without complex post-processing.

Contribution

The paper proposes GrabTab with a Component Deliberator, enabling flexible handling of complex tables and reducing reliance on post-processing, advancing TSR capabilities.

Findings

Significantly outperforms state-of-the-art methods on public benchmarks.

Effective in handling unregularized and complex table structures.

Reduces post-processing complexity in TSR tasks.

Abstract

Recently, Table Structure Recognition (TSR) task, aiming at identifying table structure into machine readable formats, has received increasing interest in the community. While impressive success, most single table component-based methods can not perform well on unregularized table cases distracted by not only complicated inner structure but also exterior capture distortion. In this paper, we raise it as Complex TSR problem, where the performance degeneration of existing methods is attributable to their inefficient component usage and redundant post-processing. To mitigate it, we shift our perspective from table component extraction towards the efficient multiple components leverage, which awaits further exploration in the field. Specifically, we propose a seminal method, termed GrabTab, equipped with newly proposed Component Deliberator. Thanks to its progressive deliberation mechanism, our GrabTab can flexibly accommodate to most complex tables with reasonable components selected but without complicated post-processing involved. Quantitative experimental results on public benchmarks demonstrate that our method significantly outperforms the state-of-the-arts, especially under more challenging scenes.