Image enhancement using one or more neural networks

Patent metadata

Field	Value
Publication number	US-12548113-B2
Application number	US-202017012000-A
Country	US
Kind code	B2
Filing date	Sep 3, 2020
Priority date	Sep 3, 2020
Publication date	Feb 10, 2026
Grant date	Feb 10, 2026

Abstract

Apparatuses, systems, and techniques are presented to generate images with one or more visual effects applied. In at least one embodiment, one or more visual effects are applied to one or more images having a resolution that is less than a first resolution and those visual effects approximated for one or more images having a resolution that is greater than or equal to the first resolution.

First claim

What is claimed is:

1 . One or more processors comprising:
circuitry to use one or more neural networks to: determine one or more parameters corresponding to a parameterized function that approximates one or more visual effects that have been applied by modifying pixel values of one or more first digital images of a first resolution; calculate one or more upsampled parameters that correspond to the one or more parameters; and cause an approximation of the one or more visual effects to be applied by modifying one or more pixel values of one or more second digital images of a second resolution, by applying the one or more upsampled parameters, the second resolution being lower than the first resolution.

2 . The one or more processors of claim 1 , wherein the one or more visual effects are approximated using the one or more neural networks.

3 . The one or more processors of claim 1 , wherein the one or more visual effects include addition of bloom, color correction, motion blur, lens flare, sharpening, filtering, chromatic aberration, lens distortion, chromatic glitch, or interface elements.

4 . The one or more processors of claim 1 , wherein the one or more parameters represent changes to one or more pixel locations, and wherein the one or more parameters can be used to determine a first parameterized function for the one or more first digital images, and wherein a second parameterized function, determined based on the first parameterized function and used to approximate the one or more visual effects for the one or more second digital images.

5 . The one or more processors of claim 4 , wherein the circuitry is further to apply one or more enhancements to the one or more second digital images after the one or more visual effects are approximated.

6 . The one or more processors of claim 1 , wherein the one or more first digital images have a resolution of an initial aliased image generated by a rendering engine.

7 . A system comprising one or more processors to:
use one or more neural networks to; determine one or more parameters corresponding to a parameterized function that approximates one or more visual effects that have been applied by modifying pixel values of one or more first digital images of a first resolution; calculate one or more upsampled parameters that correspond to the one or more parameters; and cause an approximation of the one or more visual effects to be applied by modifying one or more pixel values of one or more second digital images of a second resolution by applying the one or more upsampled parameters, the second resolution being lower than the first resolution.

8 . The system of claim 7 , wherein the one or more visual effects are approximated using the one or more neural networks.

9 . The system of claim 7 , wherein the one or more visual effects include addition of bloom, color correction, motion blur, lens flare, sharpening, filtering, chromatic aberration, lens distortion, chromatic glitch, or interface elements.

10 . The system of claim 7 , wherein the one or more parameters represent changes to one or more pixel locations, and wherein a first parameterized function is determined for the one or more first digital images, and wherein a second parameterized function is determined based on the first parameterized function and used to approximate the one or more visual effects for the one or more second digital images.

11 . The system of claim 10 , wherein the one or more processors are further to apply one or more enhancements to the one or more second digital images after the one or more visual effects are approximated.

12 . The system of claim 7 , wherein the one or more first digital images has a resolution of an initial aliased image generated by a rendering engine.

13 . A method comprising:
using one or more neural networks to; determine one or more parameters corresponding to a parameterized function that approximates one or more visual effects that have been applied by modifying pixel values of one or more first digital images of a first resolution; calculate one or more upsampled parameters that correspond to the one or more parameters; and cause an approximation of the one or more visual effects to be applied by modifying one or more pixel values of one or more second digital images of a second resolution by applying the one or more upsampled parameters, the second resolution being lower than the first resolution.

14 . The method of claim 13 , wherein the one or more visual effects are approximated using the one or more neural networks.

15 . The method of claim 13 , wherein the one or more visual effects include addition of bloom, color correction, motion blur, lens flare, sharpening, filtering, chromatic aberration, lens distortion, chromatic glitch, or interface elements.

16 . The method of claim 13 , wherein the one or more parameters represent changes to one or more pixel locations, and wherein a first parameterized function is determined for the one or more first digital images, and wherein a second parameterized function is determined based on the first parameterized function and used to approximate the one or more visual effects for the one or more second digital images.

17 . The method of claim 16 , further comprising:
applying one or more enhancements to the one or more second digital images after the one or more visual effects are approximated.

18 . The method of claim 13 , wherein the one or more first digital images has a resolution of an initial aliased image generated by a rendering engine.

19 . A non-transitory machine-readable medium having stored thereon a set of instructions, which if performed by one or more processors, cause the one or more processors to at least:
use one or more neural networks to; determine one or more parameters corresponding to a parameterized function that approximates one or more visual effects that have been applied by modifying pixel values of one or more first digital images of a first resolution; calculate one or more upsampled parameters that correspond to the one or more parameters; and cause an approximation of the one or more visual effects to be applied by modifying one or more pixel values of one or more second digital images of a second resolution by applying the one or more upsampled parameters, the second resolution being lower than the first resolution.

20 . The non-transitory machine-readable medium of claim 19 , wherein the one or more visual effects are approximated using the one or more neural networks.

21 . The non-transitory machine-readable medium of claim 19 , wherein the one or more visual effects include addition of bloom, color correction, motion blur, lens flare, sharpening, filtering, chromatic aberration, lens distortion, chromatic glitch, or interface elements.

22 . The non-transitory machine-readable medium of claim 19 , wherein the one or more parameters represent changes to one or more pixel locations, and wherein a first parameterized function is determined for the one or more first digital images, and wherein a second parameterized function is determined based on the first parameterized function and used to approximate the one or more visual effects for the one or more second digital images.

23 . The non-transitory machine-readable medium of claim 22 , wherein the instructions if performed further cause the one or more processors to:
apply one or more enhancements to the one or more second

Assignees

• Nvidia Corp

Inventors

• Pottorff Robert
• Tarjan David
• Tao Andrew
• Catanzaro Bryan

Classifications

• G06T5/80

  Geometric correction · CPC title

• G06T5/73

  Deblurring; Sharpening · CPC title

• G06T5/70

  Denoising; Smoothing · CPC title

• G06T5/20

  using local operators · CPC title

• G06T15/503

  Blending, e.g. for anti-aliasing · CPC title