cs.CVAug 23, 2026

AcroMELD: Recovering Interactive PDF Forms with Structure-Aware Graph Set Transformers

Authors: Samuel Abramov

Organizations: Accessful GmbH

Read PDF
Ask AI
Cite

Copy citation

DOINot available for this paper

Abstract

Interactive PDF form fields are often absent from documents that visually resemble forms, leaving users unable to enter data without printing or external editing tools. Detecting the missing widgets is difficult because a field may be indicated by several overlapping cues, born-digital PDFs expose useful but incomplete drawing structure, and dense pages can contain hundreds of fields. We introduce AcroMELD (AcroForm Multi-source Evidence Linking Decoder), a 39.4M-parameter detector that combines a high-resolution visual transformer with label-free PDF primitives. Its 896-query set comprises 384 visual proposals, 384 structure-seeded proposals, and 128 learned recovery queries. Four graph-set layers exchange information over geometry-biased sparse neighborhoods and cross-attend to PDF structure. A learned same-field relation links co-referent candidates, while a localization-quality head is trained on the containment-aware overlap used by the downstream recovery decision. We define a hash-bound evaluation protocol with disjoint development, calibration, internal-test, and quarantined external-holdout roles. The sealed, single-seed candidate reaches native containment micro-F1F_1 0.9344 on the internal test and 0.8477 on the one-shot external holdout (95% PDF-cluster bootstrap interval [0.8339, 0.8605]). This passes the registered historical FFGBT-v8 reference by 0.0186 absolute F1F_1. Under the stricter external adapter, however, performance is 0.7786 IoU-0.50.5 F1F_1 and 0.2900 COCO mAP, below a locally evaluated CommonForms-L reference; the signature class receives no prediction at the selected threshold. Thus the result supports the registered operational gate while exposing substantial domain and rare-class limitations.

Figures & tables

Figure 1: AcroMELD architecture. The raster and label-free PDF structure remain independent evidence channels until their heterogeneous queries enter one graph-set decoder. Dashed cross-attention makes all structure tokens available as context; solid paths produce the exclusive prediction set.
Figure 2: Development trajectory across 33 completed epochs at the fixed training-time decoder point. Left: native containment F1F_{1} , strict IoU- 0.50.5 F1F_{1} , and strict COCO mAP. Right: classwise strict COCO AP. Shading marks the three augmentation-free finale epochs. These repeatedly observed development measurements drove checkpoint selection and are not held-out learning curves.
More in this topic

Document Image Understanding

Document image understanding turns page images into recognized text, layout, structured data, and answers grounded in visual evidence.

See all 148 papers

Explore similar work

CardsList
Mar 31, 2026

AutoFormBench: Benchmark Dataset for Automating Form Understanding

Automated processing of structured documents such as government forms, healthcare records, and enterprise invoices remains a persistent challenge due to the high degree of layout variability encountered in real-world settings. This paper introduces AutoFormBench, a benchmark dataset of 407 annotated real-world forms spanning government, healthcare, and enterprise domains, designed to train and evaluate form element detection models. We present a systematic comparison of classical OpenCV approaches and four YOLO architectures (YOLOv8, YOLOv11, YOLOv26-s, and YOLOv26-l) for localizing and classifying fillable form elements. specifically checkboxes, input lines, and text boxes across diverse PDF document types. YOLOv11 demonstrates consistently superior performance in both F1 score and Jaccard accuracy across all element classes and tolerance levels.

Gaurab Baral, Junxiu Zhou

School of Computing and Analytics, Northern Kentucky University, Highland Heights, Kentucky, 41076

Document UnderstandingDocument Layout AnalysisDocument ParsingObject Detection
AskPDF
Sep 20, 2026

Mind the Gaps: A Curated Benchmark for Form Field Detection

Form Field Detection (FFD) is a fundamental component of document understanding systems, enabling applications ranging from large-scale industrial digitization to accessible form interaction for automated analysis. Unlike conventional object detection tasks, FFD is inherently challenging because fields are often defined by layout structure and whitespace rather than visible foreground content. Existing large-scale datasets frequently rely on heuristic annotation pipelines, resulting in noisy and inconsistent labels that hinder reliable evaluation. In this work, we introduce mini-CommonForms, a carefully curated FFD benchmark with consistent, high-quality annotations, and present a detailed evaluation of state-of-the-art detection approaches. The benchmark is designed to support reproducible research in document automation and accessibility-oriented applications. Dataset and code are available at https://github.com/moured/mini-commonforms

Iheb Brini, Omar Moured, Hamza Gbada +1

Luleå University of Technology, Luleå, Sweden · Karlsruhe Institute of Technology, Karlsruhe, Germany · LATIS-Laboratory of Advanced Technology and Intelligent Systems, National Engineering School of Sousse (ENISo), University of Sousse, Tunisia

Document Layout AnalysisDocument Image Understanding
AskPDF
Apr 25, 2026

Lightweight and Production-Ready PDF Visual Element Parsing

PDF documents contain critical visual elements such as figures, tables, and forms whose accurate extraction is essential for document understanding and multimodal retrieval-augmented generation (RAG). Existing PDF parsers often miss complex visuals, extract non-informative artifacts (e.g., watermarks, logos), produce fragmented elements, and fail to reliably associate captions with their corresponding elements, which degrades downstream retrieval and question answering. We present a lightweight and production level PDF parsing framework that can accurately detect visual elements and associates captions using a combination of spatial heuristics, layout analysis, and semantic similarity. On popular benchmark datasets and internal product data, the proposed solution achieves ≥96%\geq96\% visual element detection accuracy and 93%93\% caption association accuracy. When used as a preprocessing step for multimodal RAG, it significantly outperforms state-of-the-art parsers and large vision-language models on both internal data and the MMDocRAG benchmark, while reducing latency by over 2×2\times. We have deployed the proposed system in challenging production environment.

Meizhu Liu, Yassi Abbasi, Matthew Rowe +2

Oracle AI

Document ParsingDocument Layout Analysis
AskPDF