CPC G06T 19/20 (2013.01) [G06T 3/4092 (2013.01); G06T 15/04 (2013.01); G06T 17/20 (2013.01); G06T 19/006 (2013.01); G06T 2200/08 (2013.01); G06T 2200/24 (2013.01); G06T 2219/004 (2013.01); G06T 2219/2016 (2013.01)] | 18 Claims |
1. A method performed at a server, the method comprising:
extracting points from each of a plurality of images depicting different two-dimensional orientations of an item, to generate geometric data comprising geometric primitives and visual elements of the item;
generating, using the geometric data, a base model of the item;
receiving, from a user device, a request to view the item;
generating, from the base model and based on one or more input parameters, a device-specific three-dimensional (3D) model of the item by removing at least one geometric primitive from the base model while preserving one or more of the visual elements, wherein the one or more visual elements comprise at least one projection boundary, at least one surface contour, or combinations thereof,
wherein the one or more input parameters comprise:
one or more device characteristics of the user device,
a desired number of geometric primitives, and
an indication to preserve the one or more visual elements, and
wherein the device-specific 3D model comprises:
the desired number of geometric primitives, and
the preserved one or more visual elements; and
transmitting, to the user device, a data object comprising the device-specific 3D model, wherein the data object comprises data for generating a binocular rendering of the device-specific 3D model.
|