Systems and methods for generating digital media based on object feature points

Patent metadata

Field	Value
Publication number	US-11893693-B2
Application number	US-202117346448-A
Country	US
Kind code	B2
Filing date	Jun 14, 2021
Priority date	Jun 14, 2021
Publication date	Feb 6, 2024
Grant date	Feb 6, 2024

Abstract

Generating and storing digital media can be resource intensive processes. Some systems and methods disclosed herein relate to generating digital media using a pre-existing three-dimensional (3D) model of an object and feature points of the object. According to an embodiment, a method includes an e-commerce platform receiving a request for digital media depicting an object. In response to the request, the e-commerce platform may obtain a 3D model corresponding to the object and data pertaining to one or more feature points of the object. The one or more feature points may correspond to respective views of the 3D model. The e-commerce platform may then generate the digital media based on the 3D model and the one or more feature points, where the digital media could include renders of the 3D model depicting the one or more feature points.

First claim

The invention claimed is:

1. A computer-implemented method comprising:
receiving, from a merchant device, a request for digital media depicting an object;
obtaining a three-dimensional (3D) model corresponding to the object;
obtaining data pertaining to one or more feature points of the object, the one or more feature points corresponding to respective views of the 3D model, wherein the one or more feature points include a feature point corresponding to a particular location or region of the object, the feature point associated with a coordinate on a virtual surface of the 3D model in a virtual coordinate system, and wherein a vector within the virtual coordinate system is oriented in a direction towards the coordinate to define a viewpoint relative to the 3D model for rendering a view, oriented along the vector, of the particular location or region of the object including the virtual surface of the 3D model at the coordinate, wherein the viewpoint relative to the 3D model defined by the vector is determined based on both: (i) previous online user views of the object obtained by user manipulations of the 3D model corresponding to the object including a last render of the 3D model of the object presented to a user before the user added the object to their shopping cart in an online store, and (ii) input received via the merchant device; and
generating the digital media based on the 3D model and the one or more feature points, the digital media including renders of the 3D model depicting the one or more feature points, the renders including a rendered view of the viewpoint oriented along the vector to depict the particular location or region of the object, including to depict the virtual surface of the 3D model at the coordinate.

2. The method of claim 1 , wherein:
the data pertaining to the one or more feature points includes digital content corresponding to the feature point; and
generating the digital media comprises combining the digital content with the rendered view.

3. The method of claim 2 , wherein:
the digital content comprises text pertaining to the feature point; and
combining the digital content with the rendered view comprises associating the text pertaining to the feature point with a portion of the rendered view corresponding to the feature point.

4. The method of claim 2 , wherein:
the digital content comprises audio content pertaining to the feature point; and
combining the digital content with the rendered view comprises synchronizing at least a portion of the audio content with the rendered view in the digital media.

5. The method of claim 2 , wherein:
the request for the digital media is associated with a software instance on a computing system; and
obtaining the data pertaining to the one or more feature points comprises receiving the digital content from a user device associated with the software instance.

6. The method of claim 1 , wherein generating the digital media comprises generating a video of the object, the video including transitions between the renders of the 3D model depicting the one or more feature points, wherein the transitions are based on further renders of the 3D model.

7. The method of claim 1 , wherein obtaining the data pertaining to the one or more feature points comprises generating the data pertaining to one or more feature points based on stored data pertaining to the user manipulations of the 3D model.

8. The method of claim 7 , wherein:
the stored data pertaining to the user manipulations of the 3D model indicates the previous online user views of the object; and
generating the data pertaining to the one or more feature points comprises adding the feature point to the one or more feature points based on both the previous online user views of the object and the input received via the merchant device.

9. The method of claim 1 , wherein:
the request for the digital media is associated with a software instance on a computing system; and
obtaining the data pertaining to the one or more feature points comprises receiving, from a user device associated with the software instance, web content indicating user selection of at least one of the one or more feature points.

10. The method of claim 1 , further comprising:
transmitting web content comprising the digital media to a user device for display on the user device.

11. The method of claim 10 , wherein:
obtaining the data pertaining to the one or more feature points comprises generating the data pertaining to the one or more feature points based on stored data pertaining to user interactions with digital content different from the digital media, the user interactions corresponding to a particular user; and
the user device is associated with the particular user.

12. The method of claim 1 , wherein the user manipulations also comprise user magnifications, and the viewpoint relative to the 3D model defined by the vector is also determined based on user views of the object in which the object is magnified at the particular location or region of the object corresponding to the feature point.

13. A system comprising:
memory to store a three-dimensional (3D) model corresponding to an object and data pertaining to one or more feature points of the object, the one or more feature points corresponding to respective views of the 3D model, wherein the one or more feature points include a feature point corresponding to a particular location or region of the object, the feature point associated with a coordinate on a virtual surface of the 3D model in a virtual coordinate system, and wherein a vector within the virtual coordinate system is oriented in a direction towards the coordinate to define a viewpoint relative to the 3D model for rendering a view, oriented along the vector, of the particular location or region of the object including the virtual surface of the 3D model at the coordinate, wherein the viewpoint relative to the 3D model defined by the vector is determined based on both: (i) previous online user views of the object obtained by user manipulations of the 3D model corresponding to the object including a last render of the 3D model of the object presented to a user before the user added the object to their shopping cart in an online store, and (ii) input received via a merchant device; and
at least one processor to:
receive, from the merchant device, a request for digital media depicting the object; and
generate the digital media based on the 3D model and the one or more feature points, the digital media including renders of the 3D model depicting the one or more feature points, the renders including a rendered view of the viewpoint oriented along the vector to depict the particular location or region of the object, including to depict the virtual surface of the 3D model at the coordinate.

14. The system of claim 13 , wherein:
the data pertaining to the one or more feature points includes digital content corresponding to the feature point; and
the at least one processor is to combine the digital content with the rendered view in the digital media.

15. The system of claim 14 , wherein:
the digital content comprises text pertaining to the feature point; and
the at least one processor is to associate the text pertaining to the feature point with a portion of the rendered view corresponding to the feature point.

16. The system of claim 14 , wherein:
the digital content comprises audio content pertaining to the feature point; and
the at least one processor is to synchronize at least a portion of the audio content with the rendered view in the digital media.

Assignees

• Shopify Inc

Inventors

• Wade Jonathan
• Haapoja Juho Mikko
• Leroux Stephan
• Beauchamp Daniel

Classifications

• G06T19/00 Primary

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

• G06F16/44

  Browsing; Visualisation therefor · CPC title

• G06N20/00

  Machine learning · CPC title

• G06Q30/0643 Primary

  graphically representing goods, e.g. 3D product representation · CPC title

• G06T13/20

  Three-dimensional [3D] animation · CPC title