Augmented reality content rendering via albedo models, systems and methods

• US 10,192,365 B2
• Filed: 09/18/2017
• Issued: 01/29/2019
• Est. Priority Date: 05/13/2014
• Status: Active Grant

• Current Assignee: Nant Holdings IP, LLC (NantWorks, LLC)
• Original Assignee: Nant Holdings IP, LLC (NantWorks, LLC)
• Inventors: Siddiqui, Matheen, Wnuk, Kamil
• Primary Examiner(s): Gray, Ryan M
• Application Number:
  US15/707,815
• Publication Number:
  US 20180005453A1
• Time in Patent Office: 498 Days
• Field of Search: None
• CPC Class Codes: G06T 15/50 Lighting effects
• CPC Class Codes: G06T 15/80 Shading
• CPC Class Codes: G06T 17/20 Finite element generation, e.g. wire-frame surface description, tesselation
• CPC Class Codes: G06T 19/006 Mixed reality object pose determination, tracking or camera calibration for mixed reality G06T7/00
• CPC Class Codes: G06T 2200/04 involving 3D image data
• CPC Class Codes: G06T 2207/20081 Training; Learning
• CPC Class Codes: G06T 2215/16 Using real world measurements to influence rendering
• CPC Class Codes: G06T 7/20 Analysis of motion motion estimation for coding, decoding, compressing or decompressing digital video signals H04N19/43, H04N19/51
• CPC Class Codes: G06T 7/73 using feature-based methods

Abstract

Methods for rendering augmented reality (AR) content are presented. An a priori defined 3D albedo model of an object is leveraged to adjust AR content so that is appears as a natural part of a scene. Disclosed devices recognize a known object having a corresponding albedo model. The devices compare the observed object to the known albedo model to determine a content transformation referred to as an estimated shading (environmental shading) model. The transformation is then applied to the AR content to generate adjusted content, which is then rendered and presented for consumption by a user.

Claims

1. A method of rendering augmented reality content, comprising:

obtaining, by a rendering device, an albedo model related to a patient in a medical environment, the albedo model comprising portions corresponding to portions of the patient, wherein each portion of the albedo model includes lighting rules selected based on a reflective nature of a corresponding portion of the patient;

obtaining, by the rendering device, augmented reality (AR) content related to the patient;

deriving, by the rendering device, a pose of the patient or of one or more portions of the patient from a digital representation of the patient;

aligning, by the rendering device, the albedo model with the pose;

deriving, by the rendering device, observed shading data from the digital representation and the albedo model;

deriving an estimated object shading model using the albedo model and the observed shading data;

generating, by the rendering device, environmentally adjusted AR content by applying the estimated object shading model to the AR content; and

rendering, by the rendering device, the environmentally adjusted AR content.

2. The method of claim 1, wherein the portions of the patient comprise at least one of skin, a face, lips, eyes, and a tissue.

3. The method of claim 1, wherein the AR content comprises at least one of a medical image, anatomy, and a sonogram.

4. The method of claim 1, wherein the albedo model comprises a 3D albedo model.

5. The method of claim 4, wherein the predefined 3D albedo model comprises a computer-generated object model.

6. The method of claim 5, wherein the computer-generated object model comprises a mesh.

7. The method of claim 5, wherein the computer-generated object model comprises a model of a portion of the patient.

8. The method of claim 1, wherein the albedo model represents known albedo information for at least a portion of the patient.

9. The method of claim 1, wherein the albedo model comprises known features having locations within or on the patient.

10. The method of claim 9, wherein the albedo model is aligned with the pose by aligning the known features with corresponding features derived from the digital representation.

11. The method of claim 1, wherein the albedo model comprises a lighting policy including lighting rules sets associated with corresponding portions of the albedo model.

12. The method of claim 11, wherein generating the environmentally adjusted AR content includes applying at least one of the lighting rules sets to a portion of the AR content that corresponds to a portion of the albedo model.

13. The method of claim 11, wherein the lighting rules sets lighting rules for at least one of a facial feature, an article of clothing, a tissue type, a substrate, and a material type.

14. The method of claim 1, wherein the albedo model is generated from a plurality of training images captured by the rendering device of the patient in a variety of lighting conditions.

15. The method of claim 1 further comprising deriving, by the rendering device, features from a digital representation of the patient.

16. The method of claim 15, wherein the albedo model is generated from a plurality of training images captured by the rendering device of the patient from a variety of viewpoints.

17. The method of claim 16, wherein at least one of the plurality of training images correspond to the digital representation of the patient from which features are derived.

18. The method of claim 16, wherein the training images are captured by the rendering device in parallel to deriving the pose of the patient from the digital representation, and wherein the albedo model is updated at runtime as a pose alignment of each new training image is completed.

19. The method of claim 15, wherein deriving features from the digital representation includes applying at least one feature detection algorithm to the digital representation.

20. The method of claim 19, wherein the feature detection algorithm includes at least one of the following algorithms:

SIFT, BRISK, SURF, FAST, BRIEF, Harris Corners, Edges, DAISY, GLOH, HOG, EOG, and TILT.

21. The method of claim 19, wherein obtaining the AR content includes looking up the AR content based on descriptors associated with the features.

22. The method of claim 15, further comprising the rendering device capturing the digital representation.

23. The method of claim 15, further comprising tracking at least some of the features derived from the digital representation of the patient in real time.

24. The method of claim 23, wherein tracking at least some of the features includes tracking features within frames of a video sequence.

25. The method of claim 23, further comprising re-rendering the environmentally adjusted AR content in response to movement of the patient.

26. The method of claim 23, further comprising re-rendering the environmentally adjusted AR content at close to a frame rate of the video sequence.

27. The method of claim 26, wherein the frame rate is at least 30 frames per second.

28. The method of claim 15, further comprising:

using the estimated object shading model and the albedo model to generate an expected rendering of the patient;

using the digital representation of the patient and the observed shading data to identify one or more environmental artifacts in the digital representation;

rendering, by the rendering device, at least some of the one or more environmental artifacts with the environmentally adjusted AR content.

29. The method of claim 1, further comprising generating the environmentally adjusted AR content by applying a sensor environment map comprising at least one of an environment lighting map, a noise map, and a sensor error map.

30. The method of claim 1, wherein the environmentally adjusted AR content comprises an animation.

31. The method of claim 1, wherein rendering the environmentally adjusted AR content includes overlaying the environmentally adjusted AR content over an image of at least a portion of the patient.

32. The method of claim 1, wherein rendering the environmentally adjusted AR content includes presenting the environmentally adjusted AR content on a display relative to at least a portion of the patient.

33. The method of claim 1, wherein rendering the environmentally adjusted AR content includes presenting the environmentally adjusted AR content at a spatial location relative to the patient that is derived from an environmental feature implied by the estimated shading model.

34. A computer program product embedded in a non-transitory computer-readable medium comprising instructions for rendering augmented reality content, which, when executed, configure one or more computer processors to perform a method comprising:

obtaining an albedo model related to a patient in a medical environment, the albedo model comprising portions corresponding to portions of the patient, wherein each portion of the albedo model includes lighting rules selected based on a reflective nature of a corresponding portion of the patient;

obtaining augmented reality (AR) content related to the patient;

deriving a pose of the patient from a digital representation of the patient;

aligning the albedo model with the pose;

deriving observed shading data from the digital representation and the albedo model;

deriving an estimated object shading model using the albedo model and the observed shading data;

generating environmentally adjusted AR content by applying the estimated object shading model to the AR content; and

rendering the environmentally adjusted AR content.