Segmentation of surround view data

Abstract

Various examples of the present disclosure include techniques and mechanisms for generating a surround view. According to various examples, a surround view is constructed from multiple images that are captured from different locations. A computer processor is used to create a three dimensional model that includes the content and context of the surround view. In some examples, the content and context can be segmented such that separate three dimensional models can be provided for each of the content of the surround view and the context of the surround view.

What is claimed is: 
     
         1 . A method comprising:
 obtaining a first surround view of an object, wherein the first surround view includes a content and a context, wherein the first surround view includes a multi-view interactive digital media representation of the object, wherein the content includes the object and the context includes scenery surrounding the object;   selecting the content from the first surround view;   segmenting the content from the first surround view, wherein the content is separated into a distinct interactive model; and   providing a second surround view including the object without the scenery surrounding the object.   
     
     
         2 . The method of  claim 1 , wherein segmenting further includes reconstructing the content in three-dimensions from multiple camera viewpoints. 
     
     
         3 . The method of  claim 1 , wherein selecting the content is performed automatically without user input. 
     
     
         4 . The method of  claim 1 , wherein selecting the content is performed semi-automatically using user guided interaction. 
     
     
         5 . The method of  claim 1 , wherein segmenting the content includes using the context to determine parameters of the content. 
     
     
         6 . The method of  claim 1 , further comprising storing the second surround view in a database. 
     
     
         7 . The method of  claim 1 , wherein the object is a product for use in e-commerce. 
     
     
         8 . The method of  claim 1 , wherein the second surround view is an object model used for artificial intelligence training. 
     
     
         9 . The method of  claim 1 , further comprising sending data from the second surround view to a 3D printer. 
     
     
         10 . The method of  claim 1 , further comprising presenting an alternative context and providing a third surround view including the object and the alternative context, wherein the alternative context includes scenery surrounding the content. 
     
     
         11 . The method of  claim 1 , further comprising:
 selecting the context from the first surround view;   segmenting the context from the first surround view, wherein the context is separated into a distinct interactive model; and   providing a third surround view including the scenery surrounding the object but excluding the object.   
     
     
         12 . The method of  claim 10 , further comprising sending data from the third surround view to a 3D printer. 
     
     
         13 . A system comprising:
 an input interface configured to obtain a first surround view of an object, wherein the first surround view includes a content and a context, wherein the first surround view includes a multi-view interactive digital media representation of the object, wherein the content includes the object and the context includes scenery surrounding the object;   a processor configured to select the content from the first surround view and segment the content from the first surround view, wherein the content is separated into a distinct interactive model; and   an output interface configured to provide a second surround view including the object without the scenery surrounding the object.   
     
     
         14 . The system of  claim 13 , wherein segmenting further includes reconstructing the content in three-dimensions from multiple camera viewpoints. 
     
     
         15 . The system of  claim 13 , wherein selecting the content is performed automatically without user input. 
     
     
         16 . The system of  claim 13 , wherein selecting the content is performed semi-automatically using user guided interaction. 
     
     
         17 . The system of  claim 13 , wherein segmenting the content includes using the context to determine parameters of the content. 
     
     
         18 . The system of  claim 13 , further comprising storing the second surround view in a database. 
     
     
         19 . The system of  claim 13 , wherein the object is a product for use in e-commerce. 
     
     
         20 . A computer readable medium comprising:
 computer code for obtaining a first surround view of an object, wherein the first surround view includes a content and a context, wherein the first surround view includes a multi-view interactive digital media representation of the object, wherein the content includes the object and the context includes scenery surrounding the object;   computer code for selecting the content from the first surround view;   computer code for segmenting the content from the first surround view, wherein the content is separated into a distinct interactive model; and   computer code for providing a second surround view including the object without the scenery surrounding the object.