Granted Patent B2

US 12,626,335 · App. 18/352,724 · Granted May 12, 2026

Inventor: Fei Geng (Dongguan, CN)

Assignee: GUANGDONG OPPO MOBILE TELECOMMUNICATIONS CORP., LTD.

G06T5/50G06T5/70G06T5/92G06T2207/20208G06T2207/20221

Abstract

Claims (67)

1 . An image processing method, for an electronic device, the electronic device comprising an image sensor and a Pre-Image Signal Processor (Pre-ISP), and the method comprising:

acquiring, by the image sensor, an original image;

applying, by the Pre-ISP, a gain to the original image, to obtain a first image;

denoising, by the Pre-ISP, the first image to obtain a second image; and

fusing, by the Pre-ISP, the original image with the second image, to obtain a fused image, comprising:

for a first region of the second image where a brightness value is greater than a first brightness threshold and a corresponding first region of the original image, determining only the corresponding first region of the original image as a first to-be-fused image;

for a second region of the second image where the brightness value is less than a second brightness threshold and a corresponding second region of the original image, determining only the second region of the second image as a second to-be-fused image, the first brightness threshold being greater than the second brightness threshold;

for a third region of the second image where the brightness value is between the second brightness threshold and the first brightness threshold and a corresponding third region of the original image, determining both the third region of the second image and the corresponding third region of the original image as a third to-be-fused image; and

stitching the first to-be-fused image, the second to-be-fused image, and the third to-be-fused image, thereby obtaining the fused image.

2 . The method of claim 1 , wherein the Pre-ISP comprises a gain module, a denoising module and a fusion module; and

wherein applying, by the Pre-ISP, the gain to the original image to obtain a first image, comprises:

applying, by the gain module, the gain to the original image, to obtain the first image;

wherein denoising, by the Pre-ISP, the first image to obtain the second image, comprises:

denoising, by the denoising module, the first image to obtain the second image; and

wherein fusing, by the Pre-ISP, the original image and the second image to obtain the fused image, comprises:

fusing, by the fusion module, the original image with the second image, to obtain the fused image.

3 . The method of claim 2 , wherein applying, by the gain module, the gain to the original image to obtain the first image, comprises:

determining, by the gain module, a brightness parameter of the original image; and

applying, by the gain module and based on the brightness parameter, the gain to the original image, to obtain the first image; and

wherein denoising, by the denoising module, the first image to obtain the second image, comprises:

denoising, by the denoising module and based on the brightness parameter, the first image to obtain the second image.

4 . The method of claim 3 , wherein applying, based on the brightness parameter, the gain to the original image to obtain the first image, comprises:

determining, based on a value of the brightness parameter, a magnitude of the gain for the original image, wherein the smaller the value of the brightness parameter, the larger the magnitude of the gain for the original image; and the larger the value of the brightness parameter, the smaller the magnitude of the gain for the original image.

5 . The method of claim 4 , wherein determining, based on the value of the brightness parameter, the magnitude of the gain for the original image, comprises:

calculating, based on the value of the brightness parameter, a contrast of the original image; and

determining, based on the contrast of the original image, a magnitude of the gain for the original image, wherein the larger the contrast of the original image, the larger the magnitude of the gain for the original image, and the smaller the contrast of the original image, the smaller the magnitude of the gain for the original image.

6 . The method of claim 3 , wherein the original image has a plurality of brightness parameters, the plurality of brightness parameters defines a brightness value interval, the broader the brightness value interval, the smaller a magnitude of the gain applied to the original image; and the narrower the brightness value interval, the larger the magnitude of the gain applied to the original image.

7 . The method of claim 2 , wherein denoising, by the denoising module, the first image to obtain the second image, comprises:

denoising, by the denoising module, the first image based on a magnitude of the gain for the original image, to obtain the second image, wherein the larger the magnitude of the gain for the original image, the higher a degree of denoising the first image, and the smaller the magnitude of the gain for the original image, the lower the degree of denoising the first image.

8 . The method of claim 1 , wherein for the third region of the second image where the brightness value is between the second brightness threshold and the first brightness threshold and the corresponding third region of the original image, determining both the third region of the second image and the corresponding third region of the original image as the third to-be-fused image, comprises:

determining a weight parameter for the corresponding third region of the original image, and determining a weight parameter for the third region of the second image, wherein the closer the brightness value of the third region of the second image is to the first brightness threshold, the larger the weight parameter for the corresponding third region of the original image; the closer the brightness value of the third region of the second image is to the second brightness threshold, the larger the weight parameter for the third region of the second image; and

combining the corresponding third region of the original image and the third region of the second image, based on corresponding weight parameters, to obtain an image as the third to-be-fused image.

9 . The method of claim 1 , wherein acquiring, by the image sensor, the original image comprises:

taking, as the original image, an image acquired by the image sensor, in response to detecting that the electronic device fails to support a high dynamic range function.

10 . The method of claim 1 , wherein a size of the second image is the same as a size of the original image.

11 . An electronic device, comprising:

an image sensor, configured to acquire an original image, wherein the original image is acquired by the image sensor without using a high dynamic range function; and

a Pre-Image Signal Processor (Pre-ISP), configured to apply a gain to the original image, to obtain a first image; denoise the first image to obtain a second image; denoise the original image to obtain a third image; and fuse the third image with the second image, to obtain a fused image;

wherein the Pre-ISP is specifically configured to:

for a first region of the second image where a brightness value is greater than a first brightness threshold and a corresponding first region of the third image, determine only the corresponding first region of the third image as a first to-be- fused image;

for a second region of the second image where the brightness value is less than a second brightness threshold and a corresponding second region of the third image, determine only the second region of the second image as a second to-be- fused image, the first brightness threshold being greater than the second brightness threshold;

for a third region of the second image where the brightness value is between the second brightness threshold and the first brightness threshold and a corresponding third region of the third image, determine both the third region of the second image and the corresponding third region of the third image as a third to-be-fused image; and

stitch the first to-be-fused image, the second to-be-fused image, and the third to-be-fused image, thereby obtaining the fused image.

12 . The electronic device of claim 11 , wherein the Pre-ISP is configured to:

determine a brightness parameter of the original image;

apply, based on the brightness parameter, the gain to the original image, to obtain the first image; and

denoise, based on the brightness parameter, the first image to obtain the second image.

13 . The electronic device of claim 11 , wherein the Pre-ISP is configured to:

determine a weight parameter for the corresponding third region of the third image, and determine a weight parameter for the third region of the second image, wherein the closer the brightness value of the third region of the second image is to the first brightness threshold, the larger the weight parameter for the corresponding third region of the third image; the closer the brightness value of the third region of the second image is to the second brightness threshold, the larger the weight parameter for the third region of the second image; and

combine the corresponding third region of the third image and the third region of the second image, based on corresponding weight parameters, to obtain an image as the third to-be-fused image.

14 . The electronic device of claim 11 , wherein a degree of denoising applied to the original image is equal to or less than a degree of denoising applied to the first image.

15 . A non-transitory computer-readable storage medium, having program codes stored therein, wherein the program codes, when being executed by a processor, cause an image processing method to be implemented, the method comprising:

acquiring an original image, wherein the original image is acquired without using a high dynamic range function;

applying a gain to the original image, to obtain a first image;

denoising the first image to obtain a second image; and

fusing the original image with the second image, to obtain a fused image, comprising:

for a first region of the second image where a brightness value is greater than a first brightness threshold and a corresponding first region of the original image, determining only the corresponding first region of the original image as a first to-be-fused image;

for a second region of the second image where the brightness value is less than a second brightness threshold and a corresponding second region of the original image, determining only the second region of the second image as a second to-be-fused image, the first brightness threshold being greater than the second brightness threshold;

for a third region of the second image where the brightness value is between the second brightness threshold and the first brightness threshold and a corresponding third region of the original image, determining both the third region of the second image and the corresponding third region of the original image as a third to-be-fused image; and

stitching the first to-be-fused image, the second to-be-fused image, and the third to-be-fused image, thereby obtaining the fused image.

16 . The non-transitory computer-readable storage medium of claim 15 , wherein for the third region of the second image where the brightness value is between the second brightness threshold and the first brightness threshold and the corresponding third region of the original image, determining both the third region of the second image and the corresponding third region of the original image as the third to-be-fused image, comprises:

determining a weight parameter for the corresponding third region of the original image, and determining a weight parameter for the third region of the second image, wherein the closer the brightness value of the third region of the second image is to the first brightness threshold, the larger the weight parameter for the corresponding third region of the original image; the closer the brightness value of the third region of the second image is to the second brightness threshold, the larger the weight parameter for the third region of the second image; and

combining the corresponding third region of the original image and the third region of the second image, based on corresponding weight parameters, thereby obtaining the third to-be-fused image.

17 . The non-transitory computer-readable storage medium of claim 15 , wherein the applying a gain to the original image to obtain a first image, comprises:

calculating, based on a value of a brightness parameter of the original image, a contrast of the original image;

determining, based on the contrast of the original image, a magnitude of the gain for the original image; and

applying the gain of the determined magnitude to the original image, to obtain the first image, wherein the larger the contrast of the original image, the larger the magnitude of the gain for the original image, and the smaller the contrast of the original image, the smaller the magnitude of the gain for the original image.

Assignments (1)

Priority Claims (1)

Continuity (2)

References Cited (31)