Zoom action based image presentation
Aspects of the present disclosure relate to zoom action based image presentation. A zoom action on a first image can be received on a user device, the zoom action defined by a set of zoom action parameters. The first image can be analyzed to determine image properties of the first image. A second image depicting a different structural level of the first image can be searched for based on the zoom action parameters of the zoom action and the image properties of the first image. The second image can be presented to the user as a response to the received zoom action.
1 . A method comprising:
receiving, on a user device, a zoom action on a first image, the zoom action defined by a set of zoom action parameters;
analyzing, responsive to receiving the zoom action, the first image to determine image properties of the first image;
searching, within an image datastore, for a second image depicting a different structural level of the first image based on the zoom action parameters of the zoom action and the image properties of the first image;
modifying the second image to generate a third image based on the image properties of the first image; and
presenting the third image to the user as a response to the received zoom action.
2 . The method of claim 1 , wherein the second image is selected from a plurality of candidate images within the image datastore.
3 . The method of claim 1 , wherein the second image is modified to generate the third image using a generative adversarial network (GAN).
4 . The method of claim 1 , wherein the zoom action parameters include a type of zoom action, a magnitude of zoom action, and a location of zoom action within the first image.
5 . The method of claim 4 , wherein determining image properties of the first image includes:
determining a set of objects within the first image; and
determining color data associated with the first image.
6 . The method of claim 5 , wherein the second image is searched for using an object of the set of objects within the first image where the zoom action was executed as indicated by the location of the zoom action.
7 . A system comprising:
one or more processors; and
one or more computer-readable storage media collectively storing program instructions which, when executed by the one or more processors, are configured to cause the one or more processors to perform a method comprising:
receiving, on a user device, a zoom action on a first image, the zoom action defined by a set of zoom action parameters;
analyzing, responsive to receiving the zoom action, the first image to determine image properties of the first image;
searching, within an image datastore, for a second image depicting a different structural level of the first image based on the zoom action parameters of the zoom action and the image properties of the first image;
modifying the second image to generate a third image based on the image properties of the first image; and
presenting the third image to the user as a response to the received zoom action.
8 . The system of claim 7 , wherein the second image is selected from a plurality of candidate images within the image datastore.
9 . The system of claim 7 , wherein the second image is modified to generate the third image using a generative adversarial network (GAN).
10 . The system of claim 7 , wherein the zoom action parameters include a type of zoom action, a magnitude of zoom action, and a location of zoom action within the first image.
11 . The system of claim 7 , wherein determining image properties of the first image includes:
determining a set of objects within the first image; and
determining color data associated with the first image.
12 . The system of claim 11 , wherein the second image is searched for using an object of the set of objects within the first image where the zoom action was executed as indicated by a location of the zoom action.
13 . A computer program product comprising one or more computer readable storage media, and program instructions collectively stored on the one or more computer readable storage media, the program instructions comprising instructions configured to cause one or more processors to perform a method comprising:
receiving, on a user device, a zoom action on a first image, the zoom action defined by a set of zoom action parameters;
analyzing, responsive to receiving the zoom action, the first image to determine image properties of the first image;
searching, within an image datastore, for a second image depicting a different structural level of the first image based on the zoom action parameters of the zoom action and the image properties of the first image;
modifying the second image to generate a third image based on the image properties of the first image; and
presenting the third image to the user as a response to the received zoom action.
14 . The computer program product of claim 13 , wherein the second image is selected from a plurality of candidate images within the image datastore.
15 . The computer program product of claim 13 , wherein the second image is modified to generate the third image using a generative adversarial network (GAN).
16 . The computer program product of claim 13 , wherein determining image properties of the first image includes:
determining a set of objects within the first image; and
determining color data associated with the first image.
17 . The computer program product of claim 16 , wherein the second image is searched for using an object of the set of objects within the first image where the zoom action was executed as indicated by a location of the zoom action.