HybriDLA: Hybrid Generation for Document Layout Analysis

TL;DR

HybriDLA is a novel generative framework combining diffusion and autoregressive decoding to improve document layout analysis, especially for complex and diverse modern documents, achieving state-of-the-art performance.

Contribution

The paper introduces HybriDLA, a unified generative model that integrates diffusion and autoregressive decoding for enhanced document layout analysis.

Findings

Achieves 83.5% mAP on benchmark datasets.

Outperforms previous state-of-the-art methods.

Effectively handles complex and diverse document layouts.

Abstract

Conventional document layout analysis (DLA) traditionally depends on empirical priors or a fixed set of learnable queries executed in a single forward pass. While sufficient for early-generation documents with a small, predetermined number of regions, this paradigm struggles with contemporary documents, which exhibit diverse element counts and increasingly complex layouts. To address challenges posed by modern documents, we present HybriDLA, a novel generative framework that unifies diffusion and autoregressive decoding within a single layer. The diffusion component iteratively refines bounding-box hypotheses, whereas the autoregressive component injects semantic and contextual awareness, enabling precise region prediction even in highly varied layouts. To further enhance detection quality, we design a multi-scale feature-fusion encoder that captures both fine-grained and high-level visual cues. This architecture elevates performance to 83.5% mean Average Precision (mAP). Extensive experiments on the DocLayNet and M$^6$Doc benchmarks demonstrate that HybriDLA sets a state-of-the-art performance, outperforming previous approaches. All data and models will be made publicly available at https://yufanchen96.github.io/projects/HybriDLA.