ArchCAD-400K: An Open Large-Scale Architectural CAD Dataset and New Baseline for Panoptic Symbol Spotting

2025-03-28

AI Summary

Symbol recognition in architectural CAD drawings suffers from a lack of large-scale, high-quality datasets and domain-specific methods. Method: This paper introduces ArchCAD-400K—the first ultra-large-scale, open-source CAD symbol dataset (413K samples), featuring the most comprehensive category coverage and line-level instance annotations, 26× larger than the previous largest CAD dataset. We propose a fully automated annotation engine grounded in native CAD semantic parsing and formally define the novel panoptic symbol spotting task. To address it, we design DPSS, a dual-path CNN–Transformer model that jointly models line-granularity segmentation and symbol classification. Contribution/Results: On the symbol spotting benchmark, DPSS achieves a 12.7% mAP improvement over prior work, establishing new state-of-the-art performance with significantly enhanced robustness.

Technology Category

• Computer Vision: Visual Reasoning & Symbolic Representations
• Cognitive Modeling & Cognitive Systems: Symbolic Representations
• Machine Learning: Neuro-Symbolic Learning

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Recognizing symbols in architectural CAD drawings is critical for various advanced engineering applications. In this paper, we propose a novel CAD data annotation engine that leverages intrinsic attributes from systematically archived CAD drawings to automatically generate high-quality annotations, thus significantly reducing manual labeling efforts. Utilizing this engine, we construct ArchCAD-400K, a large-scale CAD dataset consisting of 413,062 chunks from 5538 highly standardized drawings, making it over 26 times larger than the largest existing CAD dataset. ArchCAD-400K boasts an extended drawing diversity and broader categories, offering line-grained annotations. Furthermore, we present a new baseline model for panoptic symbol spotting, termed Dual-Pathway Symbol Spotter (DPSS). It incorporates an adaptive fusion module to enhance primitive features with complementary image features, achieving state-of-the-art performance and enhanced robustness. Extensive experiments validate the effectiveness of DPSS, demonstrating the value of ArchCAD-400K and its potential to drive innovation in architectural design and construction.

Problem

• Automating symbol recognition in CAD drawings to reduce manual labeling.
• Creating a large-scale CAD dataset with diverse architectural drawings.
• Developing a robust baseline model for panoptic symbol spotting.

Innovation

• Automated CAD annotation engine reduces manual labeling
• Large-scale ArchCAD-400K dataset with line-grained annotations
• Dual-Pathway Symbol Spotter model enhances feature fusion