NadirFloorNet: reconstructing multi-room floorplans from a small set of registered panoramic images

We introduce a novel deep-learning approach for predicting complex indoor floor plans with ceiling heights from a minimal set of registered 360-degree images of cluttered rooms. Leveraging the broad contextual information available in a single panoramic image and the availability of annotated training datasets of room layouts, a transformer-based neural network predicts a geometric representation of each room’s architectural structure, excluding furniture and objects, and projects it on a horizontal plane (the Nadir plane) to estimate the disoccluded floor area and the ceiling heights. We then merge and process these Nadir representations on the same floor plan, using a deformable attention transformer that exploits mutual information to resolve structural occlusions and complete room reconstruction. This fully data- driven solution achieves state-of-the-art results on synthetic and real-world datasets with a minimal number of input images.

@InProceedings{PSAG25,
  author       = {Pintore, G. and Shah, U. and Agus, M. and Gobbetti, E.},
  title        = {NadirFloorNet: reconstructing multi-room floorplans from a small set of registered panoramic images},
  booktitle    = {2nd CVPR Workshop on Urban Scene Modeling},
  year         = {2025},
  publisher    = {IEEE},
  keywords     = {visual computing, data-intensive computing},
  url          = {https://publications.crs4.it/pubdocs/2025/PSAG25},
}