System and Method for Generating 2D Images of Virtual 3D Models According to Imaging Parameters Determined From 2D Images of Other Objects

Patent metadata

Field	Value
Publication number	US-2025384620-A1
Application number	US-202519316227-A
Country	US
Kind code	A1
Filing date	Sep 2, 2025
Priority date	Jul 12, 2022
Publication date	Dec 18, 2025
Grant date	—

Abstract

A system and method are provided for generating 2D electronic images of virtual 3D models using imaging parameters determined from 2D images of other objects. The method includes determining, based on one or more 2D images of a first object arranged in a particular manner, a viewpoint capable of generating the one or more 2D images of the first object arranged in the particular manner. The method also includes generating a set of one or more 2D images of a second object, the generating including rendering a virtual 3D model of the second object according to the viewpoint. Related computer-readable media are also disclosed.

First claim

1 . A computer-implemented method, comprising:
obtaining a plurality of 2D images of a first object, each arranging the first object in a corresponding particular manner, the plurality of 2D images and the corresponding arrangements of the first object providing a basis for a virtual photoshoot of a second object, wherein the first object is different from the second object; for each 2D image, determining one or more parameters of a viewpoint capable of replicating how the first object as arranged in the corresponding particular manner results in a view of the first object that corresponds to what is seen in that that 2D image; and for each determined viewpoint, generating a corresponding image of the second object by:
rendering a virtual 3D model of the second object according to the view defined by that viewpoint by positioning the virtual 3D model of the second object according to the one or more parameters determined from the corresponding 2D image of the first object; and
generating a 2D image of the second object from the rendered virtual 3D model of the second object.

2 . The method of claim 1 , further comprising:
providing an option to initiate the virtual photoshoot of the second object; and requesting the plurality of 2D images to be automatically determined.

3 . The method of claim 1 , further comprising:
providing an option to initiate the virtual photoshoot of the second object; and receiving an input providing the plurality of 2D images of the first object.

4 . The method of claim 1 , further comprising:
rendering a preview page in a user interface, the preview page comprising the plurality of 2D images generated of the second object; enabling details associated with the second object to be entered in association with the 2D images generated of the second object; and enabling the preview page to be posted for the second object.

5 . The method of claim 1 , further comprising providing an option to load the virtual 3D model of the second object.

6 . The method of claim 1 , further comprising:
determining one or more lighting parameters; and applying the one or more lighting parameters to a virtual scene comprising the virtual 3D model of the second object.

7 . The method of claim 1 , further comprising:
applying the method to a plurality of first objects and to a plurality of second objects; and generating a composite virtual scene comprising the plurality of second objects prior to generating the 2D images of the plurality of second objects.

8 . The method of claim 7 , wherein generating the composite virtual scene comprises applying at least one offset factor to arrange the plurality of second objects relative to each other.

9 . The method of claim 1 , further comprising:
rendering a virtual 3D model of at least one additional object; and capturing a plurality of 2D images of the virtual 3D model of the at least one additional object arranged according to the corresponding viewpoints.

10 . The method of claim 1 , wherein the plurality of 2D images of the first object correspond to real-world images taken of the first object.

11 . The method of claim 1 , wherein the first object and the second object are the same item, and wherein the plurality of 2D images of the first object correspond to real-world images taken of the item.

12 . The method of claim 1 , further comprising:
obtaining the plurality of 2D images of the first object; and processing the plurality of 2D images to determine the corresponding viewpoints.

13 . The method of claim 1 , further comprising:
obtaining a virtual 3D model of the first object capable of generating the plurality of 2D images of the first object each arranged in the corresponding particular manner; and determining the corresponding viewpoints from the virtual 3D model of the first object.

14 . The method of claim 13 , wherein the virtual 3D model of the first object is:
successively manipulated to approximate what is shown in the plurality of 2D images of the first object, and compared to the plurality of 2D images of the first object until a similarity criterion has been met for each corresponding viewpoint.

15 . The method of claim 1 , wherein the viewpoint comprises an orientation of the virtual 3D model.

16 . The method of claim 1 , wherein the viewpoint comprises a zoom level.

17 . The method of claim 1 , wherein the viewpoint comprises an image depth.

18 . The method of claim 1 , wherein the viewpoint is determined from a collection of 2D images of objects similar to the first object.

19 . A computer system comprising:
at least one processor; and at least one memory, the at least one memory comprising computer executable instructions that, when executed by the at least one processor, cause the system to:
obtain a plurality of 2D images of a first object, each arranging the first object in a corresponding particular manner, the plurality of 2D images and the corresponding arrangements of the first object providing a basis for a virtual photoshoot of a second object, wherein the first object is different from the second object;
for each 2D image, determine one or more parameters of a viewpoint capable of replicating how the first object as arranged in the corresponding particular manner results in a view of the first object that corresponds to what is seen in that that 2D image; and
for each determined viewpoint, generate a corresponding image of the second object by:
rendering a virtual 3D model of the second object according to the view defined by that viewpoint by positioning the virtual 3D model of the second object according to the one or more parameters determined from the corresponding 2D image of the first object; and
generating a 2D image of the second object from the rendered virtual 3D model of the second object.

20 . A computer readable medium storing computer-executable instructions that, when executed by a processor of a computer system, cause the computer system to execute instructions comprising:
obtaining a plurality of 2D images of a first object, each arranging the first object in a corresponding particular manner, the plurality of 2D images and the corresponding arrangements of the first object providing a basis for a virtual photoshoot of a second object, wherein the first object is different from the second object; for each 2D image, determining one or more parameters of a viewpoint capable of replicating how the first object as arranged in the corresponding particular manner results in a view of the first object that corresponds to what is seen in that that 2D image; and for each determined viewpoint, generating a corresponding image of the second object by:
rendering a virtual 3D model of the second object according to the view defined by that viewpoint by positioning the virtual 3D model of the second object according to the one or more parameters determined from the corresponding 2D image of the first object; and
generating a 2D image of the second object from the rendered virtual 3D model of the second object.

Assignees

• Shopify Inc

Inventors

• Leroux Stephan

Classifications

• G06T15/506

  Illumination models · CPC title

• G06T15/205 Primary

  Image-based rendering · CPC title

• G06T19/00 Primary

  Manipulating three-dimensional [3D] models or images for computer graphics · CPC title