Benchmarking Deep Learning Approaches for AEC Engineering Drawing Layout Detection and Information Extraction

• URL: http://arxiv.org/abs/2607.18997v1
• Date: Tue, 21 Jul 2026 11:30:32 GMT
• Title: Benchmarking Deep Learning Approaches for AEC Engineering Drawing Layout Detection and Information Extraction
• Abstract summary: This study constructs a custom AEC-specific layouts dataset and benchmarks five deep learning architectures.<n>Models pre-trained on general document datasets suffer from "domain interference", causing performance degradation.
• Score: 1.2964109036384739
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Information Extraction (IE) from Architecture, Engineering, and Construction (AEC) drawings remains hindered by manual inefficiency, while Layout Detection, a vital 'middleware' organizing graphical and textual hierarchies, is underexplored. General document layout models, optimized for text-centric content, lack validation on engineering drawings. This study constructs a custom AEC-specific layouts dataset and benchmarks five deep learning architectures. RF-DETR achieves state-of-the-art performance with an $mAP_{50}$ of 0.949, while the Vision-Language Model Qwen3-VL attains a leading F1-score of 0.911. Conversely, models pre-trained on general document datasets suffer from "domain interference", causing performance degradation. This establishes a robust technical foundation for automated IE in AEC.

Related papers

• BBOmix: A Tabular Benchmark for Hyperparameter Optimization of Unsupervised Biological Representation Learning [1.5538313476921937]
  $textbfBBOmix$ is the first open-source benchmark for unsupervised representation learning on real-world biological data.<n>We quantify the correlation between reconstruction loss and downstream task performance.
  arXiv  Detail & Related papers  (2026-06-03T17:48:31Z)
• Exploring Easy Boosts for Lidar Semantic Scene Completion [61.665449818739155]
  "Free lunch" strategies to boost the performance of lidar semantic scene completion (SSC) without requiring complex architectural redesigns.<n>We first demonstrate that endowing input point clouds with semantic pseudo-labels from off-the-shelf segmentors significantly improves the performance of existing architectures.
  arXiv  Detail & Related papers  (2026-06-02T17:59:59Z)
• ArtifactLinker: Linking Scientific Artifacts for Automatic State-of-the-Art Discovery [58.48859167777581]
  ArtifactLinker is a framework to automatically discover state-of-the-art (SOTA) models for datasets.<n>A benchmark named ArtifactBench with 14,053 artifacts and 51,337 relations is presented.<n>Results show that (1) graph structures between existing artifacts are effective for missing link prediction; (2) end-to-end ranking and verification with ArtifactLinker help discover potential SOTA results and research insights.
  arXiv  Detail & Related papers  (2026-05-16T09:26:08Z)
• MinerU2.5-Pro: Pushing the Limits of Data-Centric Document Parsing at Scale [92.09717763663873]
  We present MinerU2.5-Pro, which advances the state of the art purely through data engineering and training strategy design.<n>At its core is a Data Engine co-designed around coverage, informativeness, and annotation accuracy.<n>We show that MinerU2.5-Pro achieves 95.69 on OmniDocBench v1.6, improving over the same-architecture baseline by 2.71 points and surpassing all existing methods.
  arXiv  Detail & Related papers  (2026-04-06T15:44:18Z)
• MinerU2.5: A Decoupled Vision-Language Model for Efficient High-Resolution Document Parsing [117.58619053719251]
  MinerU2.5 is a document parsing model that achieves state-of-the-art recognition accuracy while maintaining exceptional computational efficiency.<n>Our approach employs a coarse-to-fine, two-stage parsing strategy that decouples global layout analysis from local content recognition.
  arXiv  Detail & Related papers  (2025-09-26T10:45:48Z)
• Extracting Structured Requirements from Unstructured Building Technical Specifications for Building Information Modeling [0.0]
  This study explores the integration of Building Information Modeling with Natural Language Processing (NLP)<n>It aims to automate the extraction of requirements from unstructured French Building Technical Specification documents within the construction industry.<n>The results indicate that CamemBERT and Fr_core_news_lg exhibited superior performance in NER, achieving F1-scores over 90%, while Random Forest proved most effective in RE, with an F1 score above 80%.
  arXiv  Detail & Related papers  (2025-08-19T13:55:41Z)
• Automated Parsing of Engineering Drawings for Structured Information Extraction Using a Fine-tuned Document Understanding Transformer [0.352650106994433]
  This paper introduces a novel hybrid deep learning framework for structured information extraction.<n>It integrates an Oriented Bounding Box (OBB) model with a transformer-based document parsing model (Donut)<n>The proposed framework improves accuracy, reduces manual effort, and supports scalable deployment in precision-driven industries.
  arXiv  Detail & Related papers  (2025-05-02T18:33:21Z)
• Unveiling Document Structures with YOLOv5 Layout Detection [0.0]
  This research investigates the utilization of YOLOv5, a cutting-edge computer vision model, for the purpose of rapidly identifying document layouts and extracting unstructured data. The main objective is to create an autonomous system that can effectively recognize document layouts and extract unstructured data.
  arXiv  Detail & Related papers  (2023-09-29T07:45:10Z)
• Enhancing Visually-Rich Document Understanding via Layout Structure Modeling [91.07963806829237]
  We propose GraphLM, a novel document understanding model that injects layout knowledge into the model. We evaluate our model on various benchmarks, including FUNSD, XFUND and CORD, and achieve state-of-the-art results.
  arXiv  Detail & Related papers  (2023-08-15T13:53:52Z)
• A Semi-Supervised Assessor of Neural Architectures [157.76189339451565]
  We employ an auto-encoder to discover meaningful representations of neural architectures. A graph convolutional neural network is introduced to predict the performance of architectures.
  arXiv  Detail & Related papers  (2020-05-14T09:02:33Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.