FloorPP-Net: Reconstructing Floor Plans using Point Pillars for Scan-to-BIM
It addresses the domain-specific problem of automating building information modeling from scans, which is incremental as it builds on existing point cloud methods.
This paper tackles the problem of reconstructing floor plans from point clouds for Scan-to-BIM applications, presenting FloorPP-Net, which achieved second runner-up in the CVPR 2021 Scan-to-BIM Challenge floor plan reconstruction track.
This paper presents a deep learning-based point cloud processing method named FloorPP-Net for the task of Scan-to-BIM (building information model). FloorPP-Net first converts the input point cloud of a building story into point pillars (PP), then predicts the corners and edges to output the floor plan. Altogether, FloorPP-Net establishes an end-to-end supervised learning framework for the Scan-to-Floor-Plan (Scan2FP) task. In the 1st International Scan-to-BIM Challenge held in conjunction with CVPR 2021, FloorPP-Net was ranked the second runner-up in the floor plan reconstruction track. Future work includes general edge proposals, 2D plan regularization, and 3D BIM reconstruction.