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

TL;DR

CADSpotting presents a robust method for panoptic symbol detection in large-scale CAD drawings by using a unified 3D point cloud model and a novel aggregation technique, significantly improving accuracy and supporting 3D reconstruction.

Contribution

The paper introduces CADSpotting, a novel approach using point cloud representation and Sliding Window Aggregation for improved symbol spotting in large CAD drawings, along with a new large-scale dataset LS-CAD.

Findings

Outperforms existing methods on benchmark datasets.

Enables automated parametric 3D interior reconstruction.

Introduces LS-CAD, a large annotated CAD dataset.

Abstract

We introduce CADSpotting, an effective method for panoptic symbol spotting in large-scale architectural CAD drawings. Existing approaches often struggle with symbol diversity, scale variations, and overlapping elements in CAD designs, and typically rely on additional features (e.g., primitive types or graphical layers) to improve performance. CADSpotting overcomes these challenges by representing primitives through densely sampled points with only coordinate attributes, using a unified 3D point cloud model for robust feature learning. To enable accurate segmentation in large drawings, we further propose a novel Sliding Window Aggregation (SWA) technique that combines weighted voting and Non-Maximum Suppression (NMS). Moreover, we introduce LS-CAD, a new large-scale dataset comprising 45 finely annotated floorplans, each covering approximately 1,000 $m^2$, significantly larger than prior benchmarks. LS-CAD will be publicly released to support future research. Experiments on FloorPlanCAD and LS-CAD demonstrate that CADSpotting significantly outperforms existing methods. We also showcase its practical value by enabling automated parametric 3D interior reconstruction directly from raw CAD inputs.