SALVe: Semantic Alignment Verification for Floorplan Reconstruction from Sparse Panoramas
This work addresses floorplan reconstruction for applications like real estate or interior design, offering a significant performance boost but is incremental as it builds on existing methods like GTSAM and HorizonNet.
The paper tackles the problem of automatic 2D floorplan reconstruction from sparse panoramas by introducing SALVe, a learned alignment verifier, resulting in over 200% improvement in completeness compared to state-of-the-art SfM systems without sacrificing accuracy, with 81% of panoramas localized in the first two connected components.
We propose a new system for automatic 2D floorplan reconstruction that is enabled by SALVe, our novel pairwise learned alignment verifier. The inputs to our system are sparsely located 360$^\circ$ panoramas, whose semantic features (windows, doors, and openings) are inferred and used to hypothesize pairwise room adjacency or overlap. SALVe initializes a pose graph, which is subsequently optimized using GTSAM. Once the room poses are computed, room layouts are inferred using HorizonNet, and the floorplan is constructed by stitching the most confident layout boundaries. We validate our system qualitatively and quantitatively as well as through ablation studies, showing that it outperforms state-of-the-art SfM systems in completeness by over 200%, without sacrificing accuracy. Our results point to the significance of our work: poses of 81% of panoramas are localized in the first 2 connected components (CCs), and 89% in the first 3 CCs. Code and models are publicly available at https://github.com/zillow/salve.