Enhanced search with morphed images

Abstract

A search system performs item searches using morphed images. A morphed image is generated using a generative model operating on two or more images of objects. A first search is performed on an item database using the morphed image as search input to identify one or more search results, which are provided for presentation. A selection of a first search result from the one or more search results is received. A further morphed image is generated using the generative model operating on an image corresponding to the first search result. A second search is performed on the item database using the further morphed image as search input to identify one or more further search results, which are provided for presentation.

What is claimed is: 
     
         1 . A computer-implemented method comprising:
 generating a morphed image using a generative model operating on two or more images of objects;   performing a first search on an item database using the morphed image as search input to identify one or more search results;   providing the one or more search results for presentation;   receiving a selection of a first search result from the one or more search results;   generating, using the generative model, a further morphed image using an image corresponding to the first search result;   performing a second search on the item database using the further morphed image as search input to identify one or more further search results; and   providing the one or more further search results for presentation.   
     
     
         2 . The computer-implemented method of  claim 1 , wherein the two or more images of objects are received from a user device. 
     
     
         3 . The computer-implemented method of  claim 1 , wherein each object from the two or more images of object corresponds to an item from the item database. 
     
     
         4 . The computer-implemented method of  claim 1 , wherein the two or more images of objects comprise objects of a single object type, and wherein the generative model comprises a generative adversarial network trained on a plurality of training images of objects of the single object type. 
     
     
         5 . The computer-implemented method of  claim 1 , wherein a plurality of morphed images are generated by the generative model, wherein a first morphed image from the plurality of morphed images shows a first object having a visual similarity closer to a first object of a first image from the two or more images of objects, and wherein a second morphed image from the plurality of morphed images shows a second object having a visual similarity closer to a second object of a second image from the two or more images of objects. 
     
     
         6 . The computer-implemented method of  claim 1 , wherein generating, using the generative model, the further morphed image using the image corresponding to the first search result comprises generating the further morphed image also using one or more selected from the following: an image from the two or more images of objects, and the morphed image. 
     
     
         7 . The computer-implemented method of  claim 1 , wherein the first search is performed on the item database using one or more additional search parameters selected from the following: a text input, a filter selection, and a user preference. 
     
     
         8 . One or more computer storage media storing computer-useable instructions that, when used by a computing device, cause the computing device to perform operations, the operations comprising:
 generating a morphed image using a generative model operating on two or more images of objects;   performing a first search on an item database using the morphed image as search input to identify one or more search results;   providing the one or more search results for presentation;   receiving a selection of a first search result from the one or more search results;   generating, using the generative model, a further morphed image using an image corresponding to the first search result;   performing a second search on the item database using the further morphed image as search input to identify one or more further search results; and   providing the one or more further search results for presentation.   
     
     
         9 . The one or more computer storage media of  claim 8 , wherein the two or more images of objects are received from a user device. 
     
     
         10 . The one or more computer storage media of  claim 8 , wherein each object from the two or more images of object corresponds to an item from the item database. 
     
     
         11 . The one or more computer storage media of  claim 8 , wherein the two or more images of objects comprise objects of a single object type, and wherein the generative model comprises a generative adversarial network trained on a plurality of training images of objects of the single object type. 
     
     
         12 . The one or more computer storage media of  claim 8 , wherein a plurality of morphed images are generated by the generative model, wherein a first morphed image from the plurality of morphed images shows a first object having a visual similarity closer to a first object of a first image from the two or more images of objects, and wherein a second morphed image from the plurality of morphed images shows a second object having a visual similarity closer to a second object of a second image from the two or more images of objects. 
     
     
         13 . The one or more computer storage media of  claim 8 , wherein generating, using the generative model, the further morphed image using the image corresponding to the first search result comprises generating the further morphed image also using one or more selected from the following: an image from the two or more images of objects, and the morphed image. 
     
     
         14 . The one or more computer storage media of  claim 8 , wherein the first search is performed on the item database using one or more additional search parameters selected from the following: a text input, a filter selection, and a user preference. 
     
     
         15 . A computer system comprising:
 a processor; and   a computer storage medium storing computer-useable instructions that, when used by the processor, causes the computer system to perform operations comprising:   generating a morphed image using a generative model operating on two or more images of objects;   performing a first search on an item database using the morphed image as search input to identify one or more search results;   providing the one or more search results for presentation;   receiving a selection of a first search result from the one or more search results;   generating, using the generative model, a further morphed image using an image corresponding to the first search result;   performing a second search on the item database using the further morphed image as search input to identify one or more further search results; and   providing the one or more further search results for presentation.   
     
     
         16 . The computer system of  claim 15 , wherein the two or more images of objects are received from a user device. 
     
     
         17 . The computer system of  claim 15 , wherein each object from the two or more images of object corresponds to an item from the item database. 
     
     
         18 . The computer system of  claim 15 , wherein the two or more images of objects comprise objects of a single object type, and wherein the generative model comprises a generative adversarial network trained on a plurality of training images of objects of the single object type. 
     
     
         19 . The computer system of  claim 15 , wherein a plurality of morphed images are generated by the generative model, wherein a first morphed image from the plurality of morphed images shows a first object having a visual similarity closer to a first object of a first image from the two or more images of objects, and wherein a second morphed image from the plurality of morphed images shows a second object having a visual similarity closer to a second object of a second image from the two or more images of objects. 
     
     
         20 . The computer system of  claim 15 , wherein generating, using the generative model, the further morphed image using the image corresponding to the first search result comprises generating the further morphed image also using one or more selected from the following: an image from the two or more images of objects, and the morphed image.