HybriDLA: Hybrid Generation for Document Layout Analysis

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 M6Doc benchmarks demonstrate that HybriDLA sets a state-of-the-art performance, outperforming previous approaches.

Authors

• Yufan Chen
• Omar Moured Karlsruhe Institute of Technology
• Ruiping Liu Institute for Anthropomatics and Robotics, Karlsruhe Institute of Technology
• Junwei Zheng Institute for Anthropomatics and Robotics, Karlsruhe Institute of Technology
• Kunyu Peng Institute for Anthropomatics and Robotics, Karlsruhe Institute of Technology
• Jiaming Zhang Institute for Anthropomatics and Robotics, Karlsruhe Institute of Technology
• Rainer Stiefelhagen Karlsruhe Institute of Technology, Karlsruhe, Germany

Keywords

No keywords are indexed for this paper.