CADSpotting: Robust Panoptic Symbol Spotting on Large-Scale CAD Drawings

2024-12-10

arXiv.org

AI Summary

Robust panoptic recognition in large-scale architectural CAD drawings is hindered by symbol diversity, scale variation, and severe element occlusion. Method: We propose a unified 3D geometric representation based on densely sampled point clouds—first modeling CAD symbols as structured point clouds endowed with spatial coordinates and color attributes—and introduce a Sliding Window Aggregation (SWA) strategy that jointly leverages weighted voting and non-maximum suppression to enhance segmentation accuracy on large-scale drawings. Contribution/Results: We construct LS-CAD, the first large-scale CAD dataset featuring single-floor plans averaging ~1000 m². Our method achieves state-of-the-art performance on both FloorPlanCAD and LS-CAD. Furthermore, it enables end-to-end parametric 3D indoor reconstruction, automating the generation of editable 3D models directly from raw CAD drawings.

Technology Category

• Computer Vision: Visual Reasoning & Symbolic Representations
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning
• Cognitive Modeling & Cognitive Systems: Symbolic Representations

Application Category

• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Search and Retrieval-Augmented AI: Web query analysis, representation and understanding

Abstract

We introduce CADSpotting, an effective method for panoptic symbol spotting in large-scale architectural CAD drawings. Existing approaches struggle with symbol diversity, scale variations, and overlapping elements in CAD designs. CADSpotting overcomes these challenges by representing primitives through densely sampled points with attributes like coordinates and colors, using a unified 3D point cloud model for robust feature learning. To enable accurate segmentation in large, complex drawings, we further propose a novel Sliding Window Aggregation (SWA) technique, combining weighted voting and Non-Maximum Suppression (NMS). Moreover, we introduce LS-CAD, a new large-scale CAD dataset to support our experiments, with each floorplan covering around 1,000 square meters, significantly larger than previous benchmarks. Experiments on FloorPlanCAD and LS-CAD datasets show that CADSpotting significantly outperforms existing methods. We also demonstrate its practical value through automating parametric 3D reconstruction, enabling interior modeling directly from raw CAD inputs.

Problem

• Detects diverse symbols in large-scale CAD drawings
• Handles scale variations and overlapping elements effectively
• Automates 3D reconstruction from raw CAD inputs

Innovation

• Uses 3D point cloud for robust feature learning
• Introduces Sliding Window Aggregation technique
• Develops large-scale CAD dataset LS-CAD