PARL: Position-Aware Relation Learning Network for Document Layout Analysis

TL;DR

PARL is an OCR-free, vision-only document layout analysis network that models intrinsic visual structure through positional and relational features, achieving state-of-the-art results with high efficiency.

Contribution

It introduces a novel vision-only framework that leverages positional and relational modeling, surpassing multimodal methods in accuracy and efficiency.

Findings

Achieves state-of-the-art performance on DocLayNet.

Outperforms multimodal models on M6Doc.

Uses significantly fewer parameters than large multimodal models.

Abstract

Document layout analysis aims to detect and categorize structural elements (e.g., titles, tables, figures) in scanned or digital documents. Popular methods often rely on high-quality Optical Character Recognition (OCR) to merge visual features with extracted text. This dependency introduces two major drawbacks: propagation of text recognition errors and substantial computational overhead, limiting the robustness and practical applicability of multimodal approaches. In contrast to the prevailing multimodal trend, we argue that effective layout analysis depends not on text-visual fusion, but on a deep understanding of documents' intrinsic visual structure. To this end, we propose PARL (Position-Aware Relation Learning Network), a novel OCR-free, vision-only framework that models layout through positional sensitivity and relational structure. Specifically, we first introduce a Bidirectional Spatial Position-Guided Deformable Attention module to embed explicit positional dependencies among layout elements directly into visual features. Second, we design a Graph Refinement Classifier (GRC) to refine predictions by modeling contextual relationships through a dynamically constructed layout graph. Extensive experiments show PARL achieves state-of-the-art results. It establishes a new benchmark for vision-only methods on DocLayNet and, notably, surpasses even strong multimodal models on M6Doc. Crucially, PARL (65M) is highly efficient, using roughly four times fewer parameters than large multimodal models (256M), demonstrating that sophisticated visual structure modeling can be both more efficient and robust than multimodal fusion.