XY-Cut++: Advanced Layout Ordering via Hierarchical Mask Mechanism on a Novel Benchmark
This addresses layout ordering for document image understanding, which is incremental but important for enhancing Retrieval-Augmented Generation and LLM preprocessing.
The paper tackles document reading order recovery for complex layouts like multi-column newspapers by introducing XY-Cut++, which integrates pre-mask processing, multi-granularity segmentation, and cross-modal matching. It achieves state-of-the-art performance with 98.8 BLEU overall, outperforming baselines by up to 24% on the new DocBench-100 dataset.
Document Reading Order Recovery is a fundamental task in document image understanding, playing a pivotal role in enhancing Retrieval-Augmented Generation (RAG) and serving as a critical preprocessing step for large language models (LLMs). Existing methods often struggle with complex layouts(e.g., multi-column newspapers), high-overhead interactions between cross-modal elements (visual regions and textual semantics), and a lack of robust evaluation benchmarks. We introduce XY-Cut++, an advanced layout ordering method that integrates pre-mask processing, multi-granularity segmentation, and cross-modal matching to address these challenges. Our method significantly enhances layout ordering accuracy compared to traditional XY-Cut techniques. Specifically, XY-Cut++ achieves state-of-the-art performance (98.8 BLEU overall) while maintaining simplicity and efficiency. It outperforms existing baselines by up to 24\% and demonstrates consistent accuracy across simple and complex layouts on the newly introduced DocBench-100 dataset. This advancement establishes a reliable foundation for document structure recovery, setting a new standard for layout ordering tasks and facilitating more effective RAG and LLM preprocessing.