SCENE SCAN

摘要

Systems, methods, and computer storage mediums are provided for creating a scene scan from a group of photographic images. An exemplary method includes determining a set of common features for at least one pair of photographic images. The features include a portion of an object captured in each of a first and a second photographic image included in the pair. The first and second photographic images may be captured from different optical centers. A similarity transform for the at least one pair of photographic images is the determined. The similarity transform is provided in order to render the scene scan from each pair of photographic images. At least one of the rotation factor, the scaling factor, or the translation factor associated with the similarity transform is used to position each pair of photographic images such that the set of common features between a pair of, at least in part, align.

主权项

1. A computer-implemented method for creating a scene scan from a group of photographic images comprising:
determining, by at least one computer processor, a set of common features for at least one pair of photographic images from the group of photographic images, the features including at least a portion of an object captured in each of a first and second photographic image included in the at least one pair of photographic images, wherein the first and second photographic images are captured from different optical centers; determining, by at least one computer processor, a similarity transform for the at least one pair of photographic images, wherein determining the similarity transform includes:
determining a rotation factor between the first and second photographic images, wherein the rotation factor describes a rotation that, when applied to the first or second photographic image, aligns, at least in part, the set of common features between the first and second photographic images;determining a scaling factor between the first and second photographic images, wherein the scaling factor describes a zoom level that, when applied to the first or second photographic image, aligns, at least in part, the set of common features between the first and second photographic images;determining a translation factor between the first and second photographic images, wherein the translation factor describes a change in position that, when applied to the first or second photographic image, aligns, at least in part, the set of common features between the first and second photographic images; and providing, by at least one computer processor, the similarity transform in order to render the scene scan from the at least one pair of photographic images, wherein at least one of the rotation factor, the scaling factor, or the translation factor associated with the similarity transform is used to position the first and second photographic images such that the set of common features between the first and second photographic images, at least in part, align; determining, by at least one computer processor, a counter rotation for the scene scan, the counter rotation based on the rotation factor and a weight factor for each photographic image included in the scene scan, wherein the weight factor for each photographic image is based on a distance of an image center of the photographic image from a center of the viewport; rendering, by at least one computer processor, the scene scan from the at least one pair of photographic images such that at least the first and second photographic images are positioned to align the set of common features between the first and second photographic images, wherein the set of common features between the first and second photographic images is aligned using at least one of the rotation factor, the scaling factor, or the translation factor; wherein rendering the scene scan includes applying the counter-rotation, at least in part, to at least one photographic image included in the scene scan, wherein the counter rotation rotates at least the one photographic image in a direction opposite to the rotation factor; and displaying at least a portion of scene scan, wherein a viewport determines the portion of the scene scan that is displayed.