Abstract: A method of automatically generating an augmented reality view of an interior space using a mobile device comprising a display screen and a video camera, and located within the interior space. The method comprises obtaining data identifying an alignment point of a virtual model of the interior space. Displaying a video image from the camera on the display screen. Outputting a request to a user to point the camera at an alignment feature of the interior space corresponding to the alignment point. In response to receiving a user input indicating that the camera is pointing at the alignment feature, capturing an image from the camera. Analyzing the captured image to identify the alignment feature in the captured image corresponding to the alignment point. Analyzing the identified alignment feature to compute a transformation required to align the alignment point of the virtual model of the interior space with the alignment feature in the captured image corresponding to the alignment point.

Abstract: A computer implemented system and method for automatically generating a training set of image comprises obtaining an image in which each pixel represents a 3 dimensional ‘3D’ point on the surface of a sphere, obtaining a projective camera model comprising a projection matrix which defines a projective transformation to map 3D points on the surface of a sphere onto an image plane based on camera model parameter values, applying the projective camera model with selected camera model parameter values to the image to produce a rectilinear image; storing the rectilinear image in association with the selected camera model parameter values; and repeating the applying and storing for different selected camera model parameter values.

Abstract: A system and method for automatically modeling a three-dimensional space based on a two-dimensional image of the three-dimensional space, by obtaining line segments corresponding to boundaries between surfaces of a three-dimensional space which are visible in a two dimensional image, identifying super-pixels and super-pixel boundaries between the super-pixels in the two-dimensional image of the three-dimensional space, and assigning a first weighting value to each identified super-pixel boundary.