Recovering 3D existing-conditions of indoor structures from spherical images

We present a vision-based approach to automatically recover the 3D existing-conditions information of an indoor structure, starting from a small set of overlapping spherical images. The recovered 3D model includes the as-built 3D room layout with the position of important functional elements located on room boundaries. We first recover the underlying 3D structure as interconnected rooms bounded by walls. This is done by combining geometric reasoning under an Augmented Manhattan World model and Structure-from-Motion. Then, we create, from the original registered spherical images, 2D rectified and metrically scaled images of the room boundaries. Using those undistorted images and the associated 3D data, we automatically detect the 3D position and shape of relevant wall-, floor-, and ceiling-mounted objects, such as electric outlets, light switches, air-vents and light points. As a result, our system is able to quickly and automatically draft an as-built model coupled with its existing conditions using only commodity mobile devices. We demonstrate the effectiveness and performance of our approach on real-world indoor scenes and publicly available datasets.