轻量级模型实现高速高精度版面表格提取
POTATR: A Lightweight Image-to-Graph Model for Page-Level Table Extraction
- 基于图像到图结构的2900万参数模型，扩展传统表格变换器
- 在PubTables-v2上达到0.964的GriTS_Con指标，速度超130倍
- 输出带边界框，支持可视化验证与多模型协同应用
大规模文档处理需要兼具准确性和效率的上下文感知表格提取。现有方法通常需数十亿参数、数百步自回归推理或高成本API调用。为此，我们提出页级对象表格变换器（POTATR），一个仅2900万参数的轻量级图像到图模型，扩展了表格变换器（TATR）以实现上下文感知的页级表格提取。POTATR在PubTables-v2单页基准测试中超越所有对比模型，包括前沿多模态大模型，取得0.964的GriTS_Con得分，同时运行速度超过130倍，成本降低约300倍。此外，POTATR输出具有空间定位：每个识别元素均附带边界框，支持视觉验证和几何文本分配。因此，POTATR实现了统一的页级表格提取，并可与其他模型组合使用，通过外部OCR扩展至扫描文档，通过跨页合并等技术延伸至整篇文档提取。代码与模型将公开发布。
原文摘要 · Abstract (English)
Large-scale document processing requires contextually aware table extraction (TE) that is both accurate and efficient. Yet current approaches require billions of parameters, hundreds of autoregressive steps, or costly API inference. Motivated by this, we introduce the Page-Object Table Transformer (POTATR), a lightweight 29M parameter image-to-graph model that extends the Table Transformer (TATR) for contextualized page-level TE. POTATR outperforms all models tested on the PubTables-v2 Single Pages benchmark -- including frontier MLLMs -- achieving $\textrm{GriTS}_\textrm{Con}$ of 0.964 while running over 130$\times$ faster at roughly 300$\times$ lower cost. Further, POTATR's output is spatially grounded: every recognized element has a bounding box, enabling visual verification and geometric text assignment. As a result, POTATR performs unified page-level TE while composing with other models, enabling extension to scanned documents via external OCR and to full-document TE via techniques like cross-page merging. Code and models will be released.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。