Pintore G., Ganovelli F., Pintus R., Scopigno R., Gobbetti E.
360 degree photography Artificial Intelligence multiroom environments Computer Vision and Pattern Recognition Spherical panoramic cameras multi-room environments Computer Graphics and Computer-Aided Design 360 degrees photography Indoor reconstruction
We present a novel approach to automatically recover, from a small set of partially overlapping spherical images, an indoor structure representation in terms of a 3D floor plan registered with a set of 3D environment maps. % We introduce several improvements over previous approaches based on color/spatial reasoning exploiting \emph{Manhattan World} priors. In particular, we introduce a new method for geometric context extraction based on a 3D facets representation, which combines color distribution analysis of individual images with sparse multi-view clues. Moreover, we introduce an efficient method to combine the facets from different points of view in a single consistent model, considering the reliability of the facets contribution. The resulting capture and reconstruction pipeline automatically generates 3D multi-room environments where most of the other previous approaches fail, such as in presence of hidden corners and large clutter, even without involving additional dense 3D data or tools. % We demonstrate the effectiveness and performance of our approach on different real-world indoor scenes. Our test data will be released to allow for further studies and comparisons.
Source: Computational visual media (Beijing. Print) 4 (2018): 367–383. doi:10.1007/s41095-018-0125-9
Publisher: Tsinghua University Press ; Springer-Verlag, Beijing ; Berlin ; Heidelberg, Cina
@article{oai:it.cnr:prodotti:392654, title = {3D floor plan recovery from overlapping spherical images}, author = {Pintore G. and Ganovelli F. and Pintus R. and Scopigno R. and Gobbetti E.}, publisher = {Tsinghua University Press ; Springer-Verlag, Beijing ; Berlin ; Heidelberg, Cina}, doi = {10.1007/s41095-018-0125-9}, journal = {Computational visual media (Beijing. Print)}, volume = {4}, pages = {367–383}, year = {2018} }