面向解析器的结构细化以实现稳定的布局接口在文档解析中
Parser-Oriented Structural Refinement for a Stable Layout Interface in Document Parsing
AI总结：
本文提出一种轻量级结构细化方法，在检测器与解析器之间稳定解析接口，通过共享的精简结构状态联合决定实例保留、精确定位和预测解析顺序，提升复杂页面的布局质量。
摘要：
准确的文档解析需要鲁棒的内容识别和稳定的解析器接口。在显式文档布局分析（DLA）流水线中，下游解析器不消耗完整的检测器输出，而是操作于保留并序列化的布局实例集。然而，在密集页面中，重叠区域和模糊边界可能导致不稳定的布局假设，使保留的实例集与解析器输入顺序不一致，导致严重的下游解析错误。为此，我们引入一个轻量级结构细化阶段，位于DETR式检测器与解析器之间，以稳定解析器接口。将原始检测器输出视为紧凑的假设池，所提模块在查询特征、语义线索、框几何和视觉证据上进行集合级推理。从共享的精简结构状态中，联合确定实例保留、精确定位和预测解析器输入顺序。我们进一步引入面向保留的监督和难度感知的顺序目标，以更好地对齐保留的实例集及其顺序与最终解析器输入，特别是在结构复杂的页面上。在公共基准上的广泛实验表明，我们的方法一致提升了页面级布局质量。当集成到标准端到端解析流水线中，稳定的解析器接口也显著减少了序列不匹配，实现了0.024的阅读顺序编辑。
英文摘要：
Accurate document parsing requires both robust content recognition and a stable parser interface. In explicit Document Layout Analysis (DLA) pipelines, downstream parsers do not consume the full detector output. Instead, they operate on a retained and serialized set of layout instances. However, on dense pages with overlapping regions and ambiguous boundaries, unstable layout hypotheses can make the retained instance set inconsistent with its parser input order, leading to severe downstream parsing errors. To address this issue, we introduce a lightweight structural refinement stage between a DETR-style detector and the parser to stabilize the parser interface. Treating raw detector outputs as a compact hypothesis pool, the proposed module performs set-level reasoning over query features, semantic cues, box geometry, and visual evidence. From a shared refined structural state, it jointly determines instance retention, refines box localization, and predicts parser input order before handoff. We further introduce retention-oriented supervision and a difficulty-aware ordering objective to better align the retained instance set and its order with the final parser input, especially on structurally complex pages. Extensive experiments on public benchmarks show that our method consistently improves page-level layout quality. When integrated into a standard end-to-end parsing pipeline, the stabilized parser interface also substantially reduces sequence mismatch, achieving a Reading Order Edit of 0.024 on OmniDocBench.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
