# US 2022/0036524 A1 · Enhanced high-dynamic-range imaging and tone mapping

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2022/0036524 A1
- Document ID: US20220036524A1
- Status: Published application
- Kind: A1
- Application number: 17/500,289
- Filed: 2021-10-13
- Published: 2022-02-03
- Earliest claimed: 2019-07-30
- Assignees: NVIDIA Corporation
- Applicants: NVIDIA Corporation
- Inventors: Yining Deng; Eric Dujardin; Hamidreza Mirzaei Domabi; Sung Hyun Hwang
- Web page: https://patentgrep.com/patent/US20220036524A1

## CPC

- G06T 5/92: based on global image properties
- G06T 2207/10024: Color image
- G06T 2207/20208: High dynamic range [HDR] image processing
- G06T 2207/30252: Vehicle exterior; Vicinity of vehicle
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL

## Abstract

The various embodiments of the present disclosure are directed towards methods for tone mapping High-Dynamic-Range (HDR) image data, as well as controlling the brightness of the image encoded by HDR the image data and/or the tone-mapped image data. HDR image is captured. A tone mapping function for the HDR image data is generated. To generate the tone mapping function, control points are dynamically determined based on an analysis of the HDR image data. The tone mapping function is fit to the control points. The tone mapping function is a non-linear function, and is described by a curve in a plane. The shape of the curve is constrained by a line generated from a portion of the control points. The tone mapping function is applied to the HDR image data. A color-compression is applied to the tone mapped image data to generate Standard Dynamic Range or Low Dynamic Range image data.

## Claims

### Claim 1

A method comprising:
determining one or more tone control points based at least on first pixel values defined by first image data;
computing a rate of change for a tone mapping function based at least on a tone control point of the one or more tone control points;
determining the tone mapping function that defines a curve corresponding to the tone control point and the rate of change; and
generating second image data defining second pixel values using the tone mapping function.

### Claim 2 (depends on 1)

The method of claim 1, wherein the tone mapping function corresponds to the rate of change at the tone control point.

### Claim 3 (depends on 1)

The method of claim 1, wherein the first image data comprises high dynamic range (HDR) image data and the generating of the second image data includes converting the HDR image data to lower dynamic range image data using the tone mapping function.

### Claim 4 (depends on 1)

The method of claim 1, wherein the tone control point is a first tone control point and the rate of change corresponds to a line passing through the first tone control point and a second tone control point of the one or more tone control points.

### Claim 5 (depends on 1)

The method of claim 1, wherein the tone control point indicates a color value to be tone mapped to a middle color value using the tone control function.

### Claim 6 (depends on 1)

The method of claim 1, wherein the determining of the tone mapping function includes fitting the tone mapping function to the one or more tone control points using the rate of change.

### Claim 7 (depends on 1)

The method of claim 1, wherein the tone control point represents a flare-suppression threshold of the tone mapping function.

### Claim 8 (depends on 1)

The method of claim 1, wherein the curve passes through a high-tone point of the one or more tone control points that defines a highlight-compression threshold of the tone mapping function.

### Claim 9 (depends on 1)

The method of claim 1, wherein the first image data was captured by at least one camera device corresponding to a vehicle and the second image data is used as input to execute one or more autonomous control operations corresponding to the vehicle.

### Claim 10

A system comprising:
one or more processing units to execute operations comprising:
determining one or more tone control points based at least on color information of first one or more images;
compute a gain value based at least on a tone control point of the one or more tone control points;
fit a tone mapping function to at least one of the one or more tone control points using the gain value; and
generating image data representative of second one or more images using the tone mapping function.

### Claim 11 (depends on 10)

The system of claim 10, wherein the tone mapping function corresponds to the gain value at the tone control point.

### Claim 12 (depends on 10)

The system of claim 10, wherein the first one or more images include one or more high dynamic range (HDR) images and the generating of the image data includes converting the one or more HDR images to one or more lower dynamic range images using the tone mapping function.

### Claim 13 (depends on 10)

The system of claim 10, wherein the tone control point is a first tone control point and the gain value corresponds to a line passing through the first tone control point and a second tone control point of the one or more tone control points.

### Claim 14 (depends on 10)

The system of claim 10, wherein the tone control point represents a flare-suppression threshold of the tone mapping function.

### Claim 15 (depends on 10)

The system of claim 10, wherein the tone mapping function defines a global tone curve constrained to pass through each of the one or more tone control points.

### Claim 16 (depends on 10)

The system of claim 10, wherein the system is incorporated in an autonomous vehicle, the autonomous vehicle comprising an image sensor that generates at least one of the first one or more images, wherein at least some of the image data is used as input to one or more deep neural networks producing outputs used to control the autonomous vehicle.

### Claim 17

A processor comprising:
one or more circuits to:
determine a gain value based at least on a tone control point of a set of tone control points defined by color information of first one or more images,
constrain a slope of a tone mapping function to correspond to the gain value using the set of tone control points, and
generate second one or more images using the tone mapping function.

### Claim 18 (depends on 17)

The processor of claim 17, wherein the one or more circuits are to compute the tone control point based at least on a quantity of mid-tone color values in the first one or more images.

### Claim 19 (depends on 17)

The processor of claim 17, wherein the set of tone control points includes a low-tone control point, a mid-tone control point, and a high-tone control point, and the slope defines a curve including the low-tone control point, the mid-tone control point, and the high-tone control point.

### Claim 20 (depends on 17)

The processor of claim 17, wherein constraining the slope of the tone mapping function includes fitting parameters of a parametric function to the set of tone control points using the gain value.

### Claim 21 (depends on 17)

The processor of claim 17, wherein the tone mapping function corresponds to the gain value at the tone control point.

### Claim 22 (depends on 17)

The processor of claim 17, wherein the tone control point is a first tone control point and the slope corresponds to a line passing through the first tone control point and a second tone control point of the set of tone control points.
