Rendering glasses shadows

• US 10,403,036 B2
• Filed: 05/22/2018
• Issued: 09/03/2019
• Est. Priority Date: 01/22/2015
• Status: Active Grant

• Current Assignee: Ditto Technologies
• Original Assignee: Ditto Technologies
• Inventors: Kornilov, Dmitry, Daugherty, Robert Charlie, Randolph, Robert Curtis, Surkov, Sergey
• Primary Examiner(s): Liu, Gordon G
• Application Number:
  US15/985,882
• Publication Number:
  US 20180374261A1
• Time in Patent Office: 469 Days
• Field of Search: 345426
• CPC Class Codes: G06Q 30/0643 Graphical representation of items or shoppers
• CPC Class Codes: G06T 15/60 Shadow generation
• CPC Class Codes: G06T 17/00 Three dimensional [3D] modelling, e.g. data description of 3D objects
• CPC Class Codes: G06T 19/00 Manipulating 3D models or images for computer graphics
• CPC Class Codes: G06V 40/171 Local features and components; Facial parts eye characteristics G06V40/18; Occluding parts, e.g. glasses; Geometrical relationships

Abstract

Rendering glasses with shadows is disclosed, including: generating a face image corresponding to an image of a set of images based at least in part on a face model, wherein the set of images is associated with a user'"'"'s face; generating a face with shadows image corresponding to the image based at least in part on shadows casted by a glasses model on the face model; generating a shadow transform based at least in part on a difference determined based at least in part on the face image and the face with shadows image; generating a shadowed image based at least in part on applying the shadow transform to the image; and presenting the shadowed image including by overlaying a glasses image associated with the glasses model over the shadowed image.

Claims

1. A system, comprising:

a processor; and

a memory coupled with the processor, wherein the memory is configured to provide the processor with instructions which when executed cause the processor to;

generate a face image corresponding to an image of a set of images based at least in part on a face model, wherein the set of images is associated with a user'"'"'s face, wherein the generating of the face image corresponding to the image of the set of images comprises to transform the face model using a set of extrinsic information corresponding to the image;

generate a face with shadows image corresponding to the image based at least in part on shadows casted by a glasses model on the face model;

generate a shadow transform based at least in part on a difference determined based at least in part on the face image and the face with shadows image, comprises to;

generate a difference image by subtracting the face image from the face with shadows image;

invert colors associated with the difference image to obtain an inverted difference image; and

determine the inverted difference image as the shadow transform;

generate a shadowed image based at least in part on applying the shadow transform to the image; and

present the shadowed image including by overlaying a glasses image associated with the glasses model over the shadowed image.

2. The system of claim 1, wherein the processor is further configured to:

obtain a three-dimensional (3D) model associated with the user'"'"'s face; and

generate a modified 3D generic face model by modifying a 3D generic face model to match the 3D model associated with the user'"'"'s face, wherein the face model comprises the modified 3D generic face model.

3. The system of claim 2, wherein the 3D model associated with the user'"'"'s face is determined from the set of images associated with the user'"'"'s face.

4. The system of claim 1, wherein to generate the face with shadows image corresponding to the image based at least in part on shadows casted by the glasses model on the face model comprises to:

transform the glasses model using the set of extrinsic information corresponding to the image;

generate a combination of the transformed face model with the transformed glasses model; and

apply a lighting model to the combination to cause the transformed glasses model to cast shadows onto the transformed face model.

5. The system of claim 4, wherein the lighting model is determined based at least in part on the set of images associated with the user'"'"'s face.

6. The system of claim 1, wherein to generate the shadow transform further comprises to apply a Despeckle filter to the inverted difference image.

7. The system of claim 1, wherein to generate the shadow transform further comprises to apply a blur filter to the inverted difference image.

8. The system of claim 1, wherein to generate the shadow transform further comprises to apply a Red Green Blue (RGB) curves filter to the inverted difference image.

9. The system of claim 1, wherein to generate the shadow transform further comprises to apply a Hue Saturation Value (HSV) filter adjustment to the inverted difference image.

10. The system of claim 1, wherein to generate the shadowed image based at least in part on applying the shadow transform to the image comprises multiplying the image with the shadow transform.

11. The system of claim 1, wherein the glasses model is associated with a pair of glasses selected by a user.

12. A method, comprising:

generating a face image corresponding to an image of a set of images based at least in part on a face model, wherein the set of images is associated with a user'"'"'s face, wherein the generating of the face image corresponding to the image of the set of images comprises transforming the face model using a set of extrinsic information corresponding to the image;

generating a face with shadows image corresponding to the image based at least in part on shadows casted by a glasses model on the face model;

generating, using a processor, a shadow transform based at least in part on a difference determined based at least in part on the face image and the face with shadows image, comprising;

generating a difference image by subtracting the face image from the face with shadows image;

inverting colors associated with the difference image to obtain an inverted difference image; and

determining the inverted difference image as the shadow transform;

generating a shadowed image based at least in part on applying the shadow transform to the image; and

presenting the shadowed image including by overlaying a glasses image associated with the glasses model over the shadowed image.

13. The method of claim 12, further comprising:

obtaining a three-dimensional (3D) model associated with the user'"'"'s face; and

generating a modified 3D generic face model by modifying a 3D generic face model to match the 3D model associated with the user'"'"'s face, wherein the face model comprises the modified 3D generic face model.

14. The method of claim 13, wherein the 3D model associated with the user'"'"'s face is determined from the set of images associated with the user'"'"'s face.

15. The method of claim 12, wherein generating the face with shadows image corresponding to the image based at least in part on shadows casted by the glasses model on the face model comprises:

transforming the glasses model using the set of extrinsic information corresponding to the image;

generating a combination of the transformed face model with the transformed glasses model; and

applying a lighting model to the combination to cause the transformed glasses model to cast shadows onto the transformed face model.

16. A computer program product, the computer program product being embodied in a non-transitory computer-readable storage medium and comprising computer instructions for:

generating a face image corresponding to an image of a set of images based at least in part on a face model, wherein the set of images is associated with a user'"'"'s face, wherein the generating of the face image corresponding to the image of the set of images comprises transforming the face model using a set of extrinsic information corresponding to the image;

generating a face with shadows image corresponding to the image based at least in part on shadows casted by a glasses model on the face model;

generating a shadow transform based at least in part on a difference determined based at least in part on the face image and the face with shadows image, comprising;

generating a difference image by subtracting the face image from the face with shadows image;

inverting colors associated with the difference image to obtain an inverted difference image; and

determining the inverted difference image as the shadow transform;

generating a shadowed image based at least in part on applying the shadow transform to the image; and

presenting the shadowed image including by overlaying a glasses image associated with the glasses model over the shadowed image.