Synthetic view for try-on experience

Patent metadata

Field	Value
Publication number	US-12417562-B2
Application number	US-202318159554-A
Country	US
Kind code	B2
Filing date	Jan 25, 2023
Priority date	Jan 25, 2023
Publication date	Sep 16, 2025
Grant date	Sep 16, 2025

Abstract

Aspects of the present disclosure involve a system for synthetically generating a view of an object to present one or more AR fashion items in an image. The system accesses a first image depicting a first portion of a body of a person from a first camera view. The system detects a fashion item in the first image that is being worn by the person in the first image, the fashion item being depicted in the first image from the first camera view. The system generates an augmented reality (AR) item that visually resembles the fashion item from the second camera view and modifies the second image with the AR item to present a synthetic view of the second portion of the body of the person wearing the AR item corresponding to the fashion item.

First claim

What is claimed is:

1. A method comprising:
accessing, by one or more processors of a device, a first image depicting a first portion of a body of a person from a first camera view;
detecting a fashion item in the first image that is being worn by the person in the first image, the fashion item being depicted in the first image from the first camera view;
generating, based on the first image, a second image that depicts a second portion of the body of the person from a second camera view;
generating, based on the fashion item detected in the first image, an augmented reality (AR) item that visually resembles the fashion item from the second camera view; and
modifying the second image with the AR item to present a synthetic view of the second portion of the body of the person wearing the AR item corresponding to the fashion item.

2. The method of claim 1 , wherein the fashion item in the first image comprises an AR fashion item.

3. The method of claim 1 , wherein the first camera view of the fashion item comprises a front view of the AR fashion item.

4. The method of claim 3 , wherein the second camera view of the fashion item comprises a side view of the AR fashion item.

5. The method of claim 1 , wherein the first portion of the body of the person comprises a front of a face of the person, and wherein the second portion of the body of the person comprises a side of the face of the person.

6. The method of claim 1 , further comprising:
applying a generative machine learning model to the first image to generate the second image.

7. The method of claim 1 , further comprising:
applying a three-dimensional (3D) rendering process to the first image to generate the second image.

8. The method of claim 1 , further comprising:
activating a front-facing camera of a device to capture a depiction of the first portion of the body of the person from the first camera view; and
synthetically generating the second image to approximate a depiction of the second portion of the body from the second camera view based on the depiction of the first portion of the body of the person from the first camera view.

9. The method of claim 1 , further comprising:
presenting the second image together with the first image.

10. The method of claim 9 , wherein the second image is overlaid on top of the first image.

11. The method of claim 9 , wherein the second image is presented adjacent to the first image.

12. The method of claim 1 , further comprising:
synthetically rotating the body of the person to generate the second image that depicts the second portion of the body of the person from the second camera view.

13. The method of claim 1 , wherein the fashion item comprises an earring, wherein the first portion of the body comprises a front view of an ear of the person wearing the earring, and wherein the synthetic view comprises a side view of the ear of the person wearing the earring.

14. The method of claim 1 , wherein the fashion item comprises a shoe, wherein the first portion of the body comprises a front view of a leg and foot of the person wearing the shoe, and wherein the synthetic view comprises a side view of the leg and foot of the person wearing the shoe.

15. The method of claim 1 , further comprising:
overlaying the AR item on top of the second image to generate the synthetic view.

16. The method of claim 1 , further comprising:
receiving input that selects the second camera view, wherein the second image and the synthetic image are generated in response to receiving the input.

17. The method of claim 1 , wherein the second camera view comprises a view of the body of the person from a closer distance to a camera relative to a distance of the body of the person to the camera corresponding to the first camera view.

18. A system comprising:
a processor of a device configured to perform operations comprising:
accessing a first image depicting a first portion of a body of a person from a first camera view;
detecting a fashion item in the first image that is being worn by the person in the first image, the fashion item being depicted in the first image from the first camera view;
generating, based on the first image, a second image that depicts a second portion of the body of the person from a second camera view;
generating, based on the fashion item detected in the first image, an augmented reality (AR) item that visually resembles the fashion item from the second camera view; and
modifying the second image with the AR item to present a synthetic view of the second portion of the body of the person wearing the AR item corresponding to the fashion item.

19. The system of claim 18 , wherein the fashion item in the first image comprises an AR fashion item.

20. A non-transitory machine-readable storage medium that includes instructions that, when executed by one or more processors of a device, cause the device to perform operations comprising:
accessing a first image depicting a first portion of a body of a person from a first camera view;
detecting a fashion item in the first image that is being worn by the person in the first image, the fashion item being depicted in the first image from the first camera view;
generating, based on the first image, a second image that depicts a second portion of the body of the person from a second camera view;
generating, based on the fashion item detected in the first image, an augmented reality (AR) item that visually resembles the fashion item from the second camera view; and
modifying the second image with the AR item to present a synthetic view of the second portion of the body of the person wearing the AR item corresponding to the fashion item.

Assignees

• Snap Inc

Inventors

• Zohar Matan
• Berg Omri
• Berger Itamar
• Sasson Gal

Classifications

• G06T2210/16

  Cloth · CPC title

• G06Q30/0643

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

• G06T11/00 Primary

  Two-dimensional [2D] image generation · CPC title

• G06T15/205

  Image-based rendering · CPC title

• G06T19/006 Primary

  Mixed reality (object pose determination, tracking or camera calibration for mixed reality G06T7/00) · CPC title