Scholarlink

<p>Classical OCR pipelines decompose document reading into detection, segmentation, and recognition stages, which makes them sensitive to localization errors and difficult to extend to interactive querying. This work investigates whether a single compact model can jointly perform text recognition and spatial grounding on both handwritten and printed documents. We introduce <b>PILOT</b>, a 155M-parameter prompt-conditioned generative model that formulates document OCR as unified sequence generation. A lightweight depthwise-separable CNN encodes the page, and a Transformer decoder autoregressively emits a single stream of subword and quantized absolute-coordinate tokens on a 10&#xa0;px grid, enabling full-page OCR, region-conditioned reading, and query-by-string spotting within the same architecture. A three-stage curriculum, progressing from plain transcription to joint text-and-box generation and finally to prompt-controlled extraction, stabilizes training and improves spatial grounding. Experiments on IAM, RIMES&#xa0;2009, SROIE&#xa0;2019, and the heterogeneous MAURDOR benchmark show that PILOT achieves competitive or superior performance in text recognition and line-level detection compared with traditional OCR systems, recent end-to-end HTR models, and compact vision–language models, while remaining substantially smaller than billion-scale multimodal models. Additional evaluations on fine-grained OCR and query-by-string spotting further confirm that a unified text–layout decoder can provide accurate and efficient promptable OCR in a compact setting. To support reproducibility, we will release the synthetic SROIE generator, the 500k annotated IDL/PDFA pages, and the harmonized line-level annotations for IAM, RIMES&#xa0;2009, and MAURDOR, with code made publicly available upon acceptance.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

PILOT: A promptable interleaved layout-aware OCR transformer

  • 期刊论文

  • 发表日期：

    2026年6月2日

查看全文
  • Laziz Hamdi,
  • Amine Tamasna,
  • Pascal Boisson,
  • Thierry Paquet

摘要

Classical OCR pipelines decompose document reading into detection, segmentation, and recognition stages, which makes them sensitive to localization errors and difficult to extend to interactive querying. This work investigates whether a single compact model can jointly perform text recognition and spatial grounding on both handwritten and printed documents. We introduce PILOT, a 155M-parameter prompt-conditioned generative model that formulates document OCR as unified sequence generation. A lightweight depthwise-separable CNN encodes the page, and a Transformer decoder autoregressively emits a single stream of subword and quantized absolute-coordinate tokens on a 10 px grid, enabling full-page OCR, region-conditioned reading, and query-by-string spotting within the same architecture. A three-stage curriculum, progressing from plain transcription to joint text-and-box generation and finally to prompt-controlled extraction, stabilizes training and improves spatial grounding. Experiments on IAM, RIMES 2009, SROIE 2019, and the heterogeneous MAURDOR benchmark show that PILOT achieves competitive or superior performance in text recognition and line-level detection compared with traditional OCR systems, recent end-to-end HTR models, and compact vision–language models, while remaining substantially smaller than billion-scale multimodal models. Additional evaluations on fine-grained OCR and query-by-string spotting further confirm that a unified text–layout decoder can provide accurate and efficient promptable OCR in a compact setting. To support reproducibility, we will release the synthetic SROIE generator, the 500k annotated IDL/PDFA pages, and the harmonized line-level annotations for IAM, RIMES 2009, and MAURDOR, with code made publicly available upon acceptance.