SepFormer: Coarse-to-fine Separator Regression Network for Table Structure Recognition
This work addresses table structure recognition for semantic data extraction, representing an incremental improvement in speed and robustness.
The paper tackles the problem of table structure recognition from images by proposing SepFormer, a coarse-to-fine separator regression network that integrates split-and-merge into a single step, achieving comparable performance to state-of-the-art methods at an average speed of 25.6 FPS on benchmark datasets.
The automated reconstruction of the logical arrangement of tables from image data, termed Table Structure Recognition (TSR), is fundamental for semantic data extraction. Recently, researchers have explored a wide range of techniques to tackle this problem, demonstrating significant progress. Each table is a set of vertical and horizontal separators. Following this realization, we present SepFormer, which integrates the split-and-merge paradigm into a single step through separator regression with a DETR-style architecture, improving speed and robustness. SepFormer is a coarse-to-fine approach that predicts table separators from single-line to line-strip separators with a stack of two transformer decoders. In the coarse-grained stage, the model learns to gradually refine single-line segments through decoder layers with additional angle loss. At the end of the fine-grained stage, the model predicts line-strip separators by refining sampled points from each single-line segment. Our SepFormer can run on average at 25.6 FPS while achieving comparable performance with state-of-the-art methods on several benchmark datasets, including SciTSR, PubTabNet, WTW, and iFLYTAB.