Image group processing and visualization

Abstract

Techniques are provided for efficiently generating 3D information from a set of digital images. Techniques are also provided for displaying groups (or clusters) of digital images using 3D information associated with the digital images. In one technique, a group of digital images are displayed as a stack of thumbnail images where the thumbnail images are aligned on a display with respect to each other based on common features identified in the digital images, camera position, and/or camera pose. In another technique, a group of digital images are organized on a display in either a 3D layout or a 2D layout based on 3D information associated with each digital image in the group. In another technique, a transition effect is generated based on projections of two digital images onto a common scene plane and blending (or cross fading) one of the 3D projections with the other of the 3D projections.

1 . (canceled) 
     
     
         2 . A system comprising:
 one or more processors coupled to a memory device, the memory device containing instructions that, when executed by the one or more processors, cause the system to:
 identify a plurality of digital images that includes a first image including a first image region and a first plurality of descriptors and a second image including a second image region and a second plurality of descriptors; 
 associate the first image with the second image, by determining that the first image region corresponds to the second image region based on the first plurality of descriptors and the second plurality of descriptors sharing at least one descriptor; 
 build a stack including the first image and the second image, in response to associating the first image with the second image, the stack including a representative image; and 
 cause to be displayed on a display screen, at least a portion of the first image as the representative image of the stack. 
   
     
     
         3 . The system of  claim 2 , further comprising instructions to cause the system to transform the second image such that the transformed second image is aligned with the representative image. 
     
     
         4 . The system of  claim 2 , wherein the at least one descriptor shared between the first plurality of descriptors and the second plurality of descriptors is a descriptor relevant to the first image region and the second image region. 
     
     
         5 . The system of  claim 2 , wherein the at least one descriptor shared between the first plurality of descriptors and the second plurality of descriptors is related to a face represented in the first image region and the second image region. 
     
     
         6 . The system of  claim 2 , wherein the plurality of digital images includes a third image including a third image region and a third plurality of descriptors; and
 further comprising instructions to cause the system to:
 associate the third image with the first image by determining that the third image region corresponds to the first image region based on the third plurality of descriptors and the first plurality of descriptors sharing at least one descriptor; and 
 add the third image to the stack in response to associating the third image with the first image. 
   
     
     
         7 . The system of  claim 6 , wherein the at least one descriptor shared by the third plurality of descriptors and the first plurality of descriptors is the at least one descriptor shared by the first plurality of descriptors and the second plurality of descriptors. 
     
     
         8 . The system of  claim 2 , further comprising instructions to cause the system to:
 receive a user input selecting at least a portion of the second image; and   cause to be displayed on the display screen, the second image region as the representative image of the stack.   
     
     
         9 . The system of  claim 2 , wherein the portion of the first image displayed as the representative image of the stack is the first image region. 
     
     
         10 . The system of  claim 2 , further comprising instructions to cause the system to cause to be displayed on the display screen, the first image in response to receiving a user input selecting the portion of the first image. 
     
     
         11 . A method comprising:
 using one or more processors:
 identifying a plurality of digital images that includes a first image including a first image region and a first plurality of descriptors and a second image including a second image region and a second plurality of descriptors; 
 associating the first image with the second image, by determining that the first image region corresponds to the second image region based on the first plurality of descriptors and the second plurality of descriptors sharing at least one descriptor; 
 building a stack including the first image and the second image, in response to associating the first image with the second image, the stack including a representative image; and 
 causing to be displayed on a display screen, at least a portion of the first image as the representative image of the stack. 
   
     
     
         12 . The method of  claim 11 , further comprising transforming the second image such that the transformed second image is aligned with the representative image. 
     
     
         13 . The method of  claim 11 , wherein the at least one descriptor shared between the first plurality of descriptors and the second plurality of descriptors is a descriptor relevant to the first image region and the second image region. 
     
     
         14 . The method of  claim 11 , wherein the at least one descriptor shared between the first plurality of descriptors and the second plurality of descriptors is related to a face represented in the first image region and the second image region. 
     
     
         15 . The method of  claim 11 , wherein the plurality of digital images includes a third image including a third image region and a third plurality of descriptors; and
 further comprising:
 associating the third image with the first image by determining that the third image region corresponds to the first image region based on the third plurality of descriptors and the first plurality of descriptors sharing at least one descriptor; and 
 adding the third image to the stack in response to associating the third image with the first image. 
   
     
     
         16 . The method of  claim 15 , wherein the at least one descriptor shared by the third plurality of descriptors and the first plurality of descriptors is the at least one descriptor shared by the first plurality of descriptors and the second plurality of descriptors. 
     
     
         17 . A non-transitory machine-readable medium comprising instructions, which when executed by at least one processor, configure the at least one processor to:
 identify a plurality of digital images that includes a first image including a first image region and a first plurality of descriptors and a second image including a second image region and a second plurality of descriptors;   associate the first image with the second image, by determining that the first image region corresponds to the second image region based on the first plurality of descriptors and the second plurality of descriptors sharing at least one descriptor;   build a stack including the first image and the second image, in response to associating the first image with the second image, the stack including a representative image; and   cause to be displayed on a display screen, at least a portion of the first image as the representative image of the stack.   
     
     
         18 . The machine-readable medium of  claim 17 , further comprising instructions to:
 receive a user input selecting at least a portion of the second image; and   cause to be displayed on the display screen, the second image region as the representative image of the stack.   
     
     
         19 . The machine-readable medium of  claim 17 , wherein the portion of the first image displayed as the representative image of the stack is the first image region. 
     
     
         20 . The machine-readable medium of  claim 17 , further comprising instructions to cause to be displayed on the display screen, the first image in response to receiving a user input selecting the portion of the first image.