| CPC G06T 1/0007 (2013.01) [G06Q 30/0643 (2013.01); G06T 11/60 (2013.01); G06V 10/235 (2022.01); G06V 10/28 (2022.01); G06V 20/20 (2022.01); G06V 20/64 (2022.01); H04N 5/2226 (2013.01); H04N 23/631 (2023.01); H04N 23/64 (2023.01); H04N 23/90 (2023.01)] | 20 Claims |

|
1. A method comprising:
receiving a first image of an item captured based at least in part on guidance to position the item within a bounded area of a user interface;
removing, by one or more processors, a portion of pixels in the first image of the item to generate a second image of the item, wherein the portion of pixels in the first image of the item are background pixels;
determining, by the one or more processors and from the second image of the item, a category of the item;
automatically selecting, by the one or more processors and based at least in part on the category of the item, a presentation layer from a plurality of presentation layers for presentation of the second image, wherein respective presentation layers of the plurality of presentation layers are associated with respective categories of items; and
causing presentation of the second image at the presentation layer of a network-based marketplace.
|