CADSpotting: Robust Panoptic Symbol Spotting on Large-Scale CAD Drawings
This work addresses a domain-specific problem for architectural design and automation by improving symbol spotting in CAD drawings, though it is incremental as it builds on existing methods with novel techniques.
The paper tackles the problem of panoptic symbol spotting in large-scale architectural CAD drawings, which is challenging due to symbol diversity, scale variations, and overlapping elements, and introduces CADSpotting, a method that outperforms existing approaches on benchmarks like FloorPlanCAD and LS-CAD, enabling automated parametric 3D interior reconstruction from raw CAD inputs.
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.