Analysis and manipulation of objects and layers in surround views

Abstract

Various embodiments of the present invention relate generally to systems and methods for analyzing and manipulating images and video. According to particular embodiments, the spatial relationship between multiple images and video is analyzed together with location information data, for purposes of creating a representation referred to herein as a surround view for presentation on a device. An object included in the surround view may be manipulated along axes by manipulating the device along corresponding axes. In particular embodiments, a surround view can be separated into layers. Effects can be applied to one or more of these layers to enhance the interactive and immersive viewing experience of the surround view.

1 . A method comprising:
 generating first surround view of an object, the first surround view corresponding to a multi-view interactive digital media representation of the object, wherein the first surround view includes a first layer corresponding to a first content model and a second layer corresponding to a first context model, wherein the first layer includes a first depth corresponding to the object and the second layer includes a second depth corresponding to scenery surrounding the object; and   comparing the first surround view of the object to a second surround view, wherein the first and second surround view correspond to multi-view interactive digital media representations, wherein comparing the first surround view to the second surround view comprises comparing the first content model to the second content model.   
     
     
         2 . The method of  claim 1 , wherein generating the first surround view of the object comprises:
 obtaining a plurality of images having location information, wherein the plurality of images include at least a portion of overlapping subject matter; and   fusing the plurality of images into the first content model and the first context model, wherein the first content model includes the object and the first context model includes scenery surrounding the object.   
     
     
         3 . The method of  claim 2 , wherein generating the first surround view of the object comprises applying an enhancement algorithm to the first content model and the first context model. 
     
     
         4 . The method of  claim 1 , wherein comparing the first surround view to the second surround view comprises:
 comparing first texture information associated with the first surround view to second texture information associated with the second surround view; and   determining whether first measurement information associated with the first content model dimensionally fits second measurement information associated with the second content model.   
     
     
         5 . The method of  claim 4 , wherein comparing the first surround view to the second surround view comprises;
 comparing the first context model to the second context model; and   associating the second surround view to a ranking in a list of matching results.   
     
     
         6 . The method of  claim 1 , wherein a modified first surround view is generated by selecting the first layer from the first surround view and applying an effect to the first layer to produce a modified first layer, wherein the second layer remains unmodified by the effect, wherein the modified first layer and the second layer is used to generated the modified first surround view. 
     
     
         7 . The method of  claim 1 , wherein the first content model is segmented out of the first surround view and a modified first surround view is generated without the scenery surrounding the object. 
     
     
         8 . The method of  claim 1 , wherein the first content model is segmented out of the first surround view and a modified first surround view is generated using a different context model to place the object in different scenery. 
     
     
         9 . The method of  claim 2 , wherein the plurality of images are obtained from a plurality of users. 
     
     
         10 . The method of  claim 2 , wherein the first surround view is a locally concave surround view. 
     
     
         11 . The method of  claim 1 , wherein the first surround view is a locally convex surround view. 
     
     
         12 . A computer readable medium comprising:
 computer code for generating first surround view of an object, the first surround view corresponding to a multi-view interactive digital media representation of the object, wherein the first surround view includes a first layer corresponding to a first content model and a second layer corresponding to a first context model, wherein the first layer includes a first depth corresponding to the object and the second layer includes a second depth corresponding to scenery surrounding the object; and   computer code for comparing the first surround view of the object to a second surround view, wherein the first and second surround view correspond to multi-view interactive digital media representations, wherein comparing the first surround view to the second surround view comprises comparing the first content model to the second content model.   
     
     
         13 . The computer readable medium of  claim 12 , wherein generating the first surround view of the object comprises:
 obtaining a plurality of images having location information, wherein the plurality of images include at least a portion of overlapping subject matter; and   fusing the plurality of images into the first content model and the first context model, wherein the first content model includes the object and the first context model includes scenery surrounding the object.   
     
     
         14 . The computer readable medium of  claim 13 , wherein generating the first surround view of the object comprises applying an enhancement algorithm to the first content model and the first context model. 
     
     
         15 . The computer readable medium of  claim 12 , wherein comparing the first surround view to the second surround view comprises:
 comparing first texture information associated with the first surround view to second texture information associated with the second surround view; and   determining whether first measurement information associated with the first content model dimensionally fits second measurement information associated with the second content model.   
     
     
         16 . The computer readable medium of  claim 15 , wherein comparing the first surround view to the second surround view comprises;
 comparing the first context model to the second context model; and   associating the second surround view to a ranking in a list of matching results.   
     
     
         17 . The computer readable medium of  claim 12 , wherein a modified first surround view is generated by selecting the first layer from the first surround view and applying an effect to the first layer to produce a modified first layer, wherein the second layer remains unmodified by the effect, wherein the modified first layer and the second layer is used to generated the modified first surround view. 
     
     
         18 . The computer readable medium of  claim 12 , wherein the first content model is segmented out of the first surround view and a modified first surround view is generated without the scenery surrounding the object. 
     
     
         19 . The computer readable medium of  claim 12 , wherein the first content model is segmented out of the first surround view and a modified first surround view is generated using a different context model to place the object in different scenery. 
     
     
         20 . A system comprising:
 means for generating first surround view of an object, the first surround view corresponding to a multi-view interactive digital media representation of the object, wherein the first surround view includes a first layer corresponding to a first content model and a second layer corresponding to a first context model, wherein the first layer includes a first depth corresponding to the object and the second layer includes a second depth corresponding to scenery surrounding the object; and   means for comparing the first surround view of the object to a second surround view, wherein the first and second surround view correspond to multi-view interactive digital media representations, wherein comparing the first surround view to the second surround view comprises comparing the first content model to the second content model.