Inferred shading mechanism

Patent metadata

Field	Value
Publication number	US-12243157-B2
Application number	US-202418610369-A
Country	US
Kind code	B2
Filing date	Mar 20, 2024
Priority date	Sep 25, 2020
Publication date	Mar 4, 2025
Grant date	Mar 4, 2025

Abstract

An apparatus to facilitate inferred object shading is disclosed. The apparatus comprises one or more processors to receive rasterized pixel data and hierarchical data associated with one or more objects and perform an inferred shading operation on the rasterized pixel data, including using one or more trained neural networks to perform texture and lighting on the rasterized pixel data to generate a pixel output, wherein the one or more trained neural networks uses the hierarchical data to learn a three-dimensional (3D) geometry, latent space and representation of the one or more objects.

First claim

What is claimed is:

1. An apparatus comprising one or more processors to receive rasterized pixel data and hierarchical data associated with one or more objects and execute one or more neural networks to generate an inferred shading of the one or more objects based on the hierarchical data.

2. The apparatus of claim 1 , wherein the one or more neural networks uses the hierarchical data to learn a three-dimensional (3D) geometry and latent space of the one or more objects.

3. The apparatus of claim 2 , wherein the hierarchical data comprises metadata that each pixel in the rasterized pixel data to be mapped to a corresponding vertex, triangle, instance identifier of an object and an object identifier.

4. The apparatus of claim 1 , wherein the hierarchical data and the rasterized pixel data are received in parallel.

5. The apparatus of claim 1 , wherein generating the inferred shading comprises the one or more neural networks performing texturing and shading to generate an output for each of the one or more objects.

6. The apparatus of claim 5 , wherein each of the one or more neural networks is associated with a different material and shading option.

7. The apparatus of claim 5 wherein the one or more neural networks comprise a first network to generate a first pixel output and a second network to generate a network pixel output.

8. The apparatus of claim 1 , wherein the inferred shading adjusts latent space parameters to generate updated texture and material properties associated with the one or more objects.

9. The apparatus of claim 1 , wherein the one or more processors further perform post-processing via an inferred shading operation.

10. A method comprising:
receiving rasterized pixel data associated with one or more objects;
receiving hierarchical data associated with the one or more objects; and
generating an inferred shading of the one or more objects based on the hierarchical data.

11. The method of claim 10 , wherein the one or more neural networks uses the hierarchical data to learn a three-dimensional (3D) geometry and latent space of the one or more objects.

12. The method of claim 11 , wherein the hierarchical data comprises metadata that each pixel in the rasterized pixel data to be mapped to a corresponding vertex, triangle, instance identifier of an object and an object identifier.

13. The method of claim 10 , wherein generating the inferred shading comprises the one or more neural networks performing texturing and shading to generate an output for each of the one or more objects.

14. The method of claim 13 , wherein each of the one or more neural networks is associated with a different material and shading option.

15. The method of claim 10 , further comprising performing post-processing via an inferred shading operation.

16. At least one non-transitory computer-readable medium having instructions stored thereon, which when executed by one or more processors, cause the processors to:
receive rasterized pixel data associated with one or more objects;
receive hierarchical data associated with the one or more objects; and
generate an inferred shading of the one or more objects based on the hierarchical data.

17. The computer-readable medium of claim 16 , wherein the one or more neural networks uses the hierarchical data to learn a three-dimensional (3D) geometry and latent space of the one or more objects.

18. The computer-readable medium of claim 17 , wherein the hierarchical data comprises metadata that each pixel in the rasterized pixel data to be mapped to a corresponding vertex, triangle, instance identifier of an object and an object identifier.

19. The computer-readable medium of claim 16 , wherein generating the inferred shading comprises the one or more neural networks performing texturing and shading to generate an output for each of the one or more objects.

20. The computer-readable medium of claim 16 , wherein the inferred shading operation to adjust latent space parameters to generate updated texture and material properties associated with the one or more objects.

Assignees

• Intel Corp

Inventors

• Panneer Selvakumar
• Mrutunjayya Mrutunjayya
• Marshall Carl S
• Iyer Ravishankar
• Waters Zack

Classifications

• G06N3/09

  Supervised learning · CPC title

• G06N3/094

  Adversarial learning · CPC title

• G06N3/0464

  Convolutional networks [CNN, ConvNet] · CPC title

• G06N3/0475

  Generative networks · CPC title

• G06T15/005 Primary

  General purpose rendering architectures · CPC title