# US 2024/0205376 A1 · Image processing method and apparatus, computer device, and storage medium

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

- Number: US 2024/0205376 A1
- Document ID: US20240205376A1
- Status: Published application
- Kind: A1
- Application number: 18/587,667
- Filed: 2024-02-26
- Published: 2024-06-20
- Earliest claimed: 2022-09-30
- Assignees: Tencent Technology (Shenzhen) Company Limited
- Applicants: Tencent Technology (Shenzhen) Company Limited
- Inventors: Yonglin LUO; Chang LIU; Lei SUN; Zirong ZHU
- Web page: https://patentgrep.com/patent/US20240205376A1

## CPC

- H04N 9/646: {for image enhancement, e.g. vertical detail restoration, cross-colour elimination, contour correction, chrominance trapping filters}
- G06T 5/50: using two or more images, e.g. averaging or subtraction
- G06T 5/92: based on global image properties
- H04N 5/268: Signal distribution or switching
- G06T 2207/10016: Video; Image sequence
- G06T 2207/20208: High dynamic range [HDR] image processing
- G06T 2207/20221: Image fusion; Image merging
- H04N: PICTORIAL COMMUNICATION, e.g. TELEVISION
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL

## Abstract

In an image processing method, for each video image of a plurality of video images of an original video, a first image generated by format conversion of the respective video image is acquired. The respective video image is represented by a first color representation. The first image is represented by a second color representation. An image dynamic range supported by the second color representation is wider than an image dynamic range supported by the first color representation. An image dynamic range of the first image is the same as an image dynamic range of the respective video image. A second image that is based on the respective video image is acquired. The second image is represented by the second color representation. An image dynamic range of the second image is wider than the image dynamic range of the respective video image. A fusion weight value of each pixel of a plurality of pixels in a target image is determined according to a display order of the respective video image in the original video, the target image being one of the first image and the second image. A fusion weight map is generated based on the fusion weight value of each pixel of the plurality of pixels in the target image. A fusion image corresponding to the respective video image is generated based on the target image, a base image, and the fusion weight map, the base image being another one of the first image and the second image. A fusion video is generated based on the fusion images corresponding to the plurality of video images.

## Claims

### Claim 1

An image processing method, comprising:
for each video image of a plurality of video images of an original video,
acquiring a first image generated by format conversion of the respective video image, the respective video image being represented by a first color representation, the first image being represented by a second color representation, an image dynamic range supported by the second color representation being wider than an image dynamic range supported by the first color representation, and an image dynamic range of the first image being the same as an image dynamic range of the respective video image;
acquiring a second image that is based on the respective video image, the second image being represented by the second color representation, and an image dynamic range of the second image being wider than the image dynamic range of the respective video image;
determining a fusion weight value of each pixel of a plurality of pixels in a target image according to a display order of the respective video image in the original video, the target image being one of the first image and the second image;
generating a fusion weight map based on the fusion weight value of each pixel of the plurality of pixels in the target image;
generating a fusion image corresponding to the respective video image based on the target image, a base image, and the fusion weight map, the base image being another one of the first image and the second image; and
generating a fusion video based on the fusion images corresponding to the plurality of video images.

### Claim 2 (depends on 1)

The method according to claim 1, wherein the determining the fusion weight value of each pixel of the plurality of pixels in the target image comprises:
determining a first quantity of the plurality of video images between a starting image in the original video and the respective video image;
determining the fusion weight values of the plurality of pixels in the target image according to the first quantity, the fusion weight values of the plurality of pixels being in a positive correlation with the first quantity; and
generating the fusion weight map corresponding to the target image based on the fusion weight values of the plurality of pixels in the target image.

### Claim 3 (depends on 2)

The method according to claim 2, wherein the determining the fusion weight values of the plurality of pixels in the target image according to the first quantity comprises:
determining a second quantity of the plurality of video images between the starting image and an end image in the original video; and
determining the fusion weight values of the plurality of pixels in the target image according to a relative relationship between the first quantity and the second quantity.

### Claim 4 (depends on 3)

The method according to claim 3, wherein the determining the fusion weight values of the plurality of pixels in the target image according to the relative relationship comprises:
obtaining first initial weight values of the plurality of pixels in the target image according to a ratio of the first quantity to the second quantity; and
adjusting the first initial weight values of the plurality of pixels in the target image according to a preset weight adjustment value, to obtain the fusion weight values of the plurality of pixels in the target image.

### Claim 5 (depends on 4)

The method according to claim 4, wherein
the fusion weight value for each pixel of the plurality of pixels in the target image is equal to the first initial weight value of the respective pixel multiplied by the preset weight adjustment value.

### Claim 6 (depends on 2)

The method according to claim 2, wherein the determining the fusion weight values of the plurality of pixels in the target image according to the first quantity comprises:
determining a first image area from the base image;
determining a second image area from the target image according to a position of the first image area in the base image;
determining a second quantity of the plurality of video images between the starting image and an end image in the original video;
determining second initial weight values of the plurality of pixels in the second image area according to a ratio of the first quantity to the second quantity;
determining a first preset value as a second initial weight value of each pixel outside the second image area in the target image; and
determining the fusion weight values of the plurality of pixels in the target image based on the second initial weight values of the plurality of pixels in the target image.

### Claim 7 (depends on 6)

The method according to claim 6, wherein the determining the fusion weight values of the plurality of pixels in the target image based on the second initial weight values of the plurality of pixels in the target image comprises:
smoothing the second initial weight values of the plurality of pixels in the target image, to obtain the fusion weight values of the plurality of pixels in the target image.

### Claim 8 (depends on 1)

The method according to claim 1, wherein the acquiring the second image comprises:
performing image enhancement processing on the first image to obtain the second image, the image enhancement processing being configured to widen an image dynamic range.

### Claim 9 (depends on 1)

The method according to claim 1, wherein the generating the fusion image comprises:
for each pixel position in the respective image,
determining a pixel at the respective pixel position in the base image,
determining a fusion weight value of the pixel at the respective pixel position in the base image according to the fusion weight value of the pixel at the respective pixel position in the target image, and
determining a fusion pixel value at the respective pixel position based on the fusion weight value of the pixel at the respective pixel position in the target image and the fusion weight value of the pixel at the respective pixel position in the base image; and
generating a fusion image corresponding to the respective video image based on the fusion pixel value at each pixel position in the respective image.

### Claim 10 (depends on 1)

The method according to claim 1, further comprising:
playing a first video, the first video being represented by the first color representation;
receiving a video switching instruction;
determining, in response to the video switching instruction, a transition period from responding to the video switching instruction to switching to a second video, and extracting a video clip of the transition period from the first video, to obtain the original video, the second video being represented by the second color representation;
switching from playing the first video to playing the fusion video, at the beginning of the transition period; and
switching to playing the second video after the transition period ends.

### Claim 11 (depends on 10)

The method according to claim 10, wherein the switching to playing the second video after the transition period ends comprises:
switching to playing the second video after the playing the fusion video ends.

### Claim 12

An image processing method, further comprising:
generating a first image by performing format conversion on an original image, the original image being represented by a first color representation, the first image being represented by a second color representation, and an image dynamic range supported by the second color representation being wider than an image dynamic range supported by the first color representation;
acquiring a second image that is based on the original image, the second image being represented by the second color representation, and an image dynamic range of the second image being wider than an image dynamic range of the original image;
determining a first image area from a source image, the source image being one of the first image and the second image;
determining a second image area from a destination image according to a position of the first image area in the source image, the destination image being another one of the first image and the second image;
smoothing an original weight value of each pixel of a plurality of pixels in the destination image, to obtain target weight values of the plurality of pixels in the destination image; and
generating a fusion image corresponding to the original image based on the destination image, the source image, and the target weight values of the plurality of pixels in the destination image.

### Claim 13 (depends on 12)

The method according to claim 12, wherein the acquiring the second image comprises:
performing image enhancement processing on the first image to obtain the second image, the image enhancement processing being configured to widen an image dynamic range.

### Claim 14 (depends on 12)

The method according to claim 12, wherein the smoothing the original weight value of each pixel of the plurality of pixels in the destination image comprises:
smoothing the original weight value of each pixel of the plurality of pixels, to obtain smoothed weight values of the plurality of pixels in the destination image; and
adjusting the smoothed weight values of the plurality of pixels in the destination image based on a preset weight adjustment value, to obtain the target weight values of the plurality of pixels in the destination image.

### Claim 15 (depends on 14)

The method according to claim 14, wherein
the target weight value of each of the plurality of pixels in the destination image is equal to the smoothed weight value of the respective pixel multiplied by the preset weight adjustment value.

### Claim 16

An image processing apparatus, comprising:
processing circuitry configured to:
for each video image of a plurality of video images of an original video,
acquire a first image generated by format conversion of the respective video image, the respective video image being represented by a first color representation, the first image being represented by a second color representation, an image dynamic range supported by the second color representation being wider than an image dynamic range supported by the first color representation, and an image dynamic range of the first image being the same as an image dynamic range of the respective video image,
acquire a second image that is based on the respective video image, the second image being represented by the second color representation, and an image dynamic range of the second image being wider than the image dynamic range of the respective video image,
determine a fusion weight value of each pixel of a plurality of pixels in a target image according to a display order of the respective video image in the original video, the target image being one of the first image and the second image,
generate a fusion weight map based on the fusion weight value of each pixel of the plurality of pixels in the target image, and
generate a fusion image corresponding to the respective video image based on the target image, a base image, and the fusion weight map, the base image being another one of the first image and the second image; and
generate a fusion video based on the fusion images corresponding to the plurality of video images.

### Claim 17 (depends on 16)

The image processing apparatus according to claim 16, wherein the processing circuitry is configured to:
determine a first quantity of the plurality of video images between a starting image in the original video and the respective video image;
determine the fusion weight values of the plurality of pixels in the target image according to the first quantity, the fusion weight values of the plurality of pixels being in a positive correlation with the first quantity; and
generate the fusion weight map corresponding to the target image based on the fusion weight values of the plurality of pixels in the target image.

### Claim 18 (depends on 17)

The image processing apparatus according to claim 17, wherein the processing circuitry is configured to:
determine a second quantity of the plurality of video images between the starting image and an end image in the original video; and
determine the fusion weight values of the plurality of pixels in the target image according to a relative relationship between the first quantity and the second quantity.

### Claim 19 (depends on 18)

The image processing apparatus according to claim 18, wherein the processing circuitry is configured to:
obtain first initial weight values of the plurality of pixels in the target image according to a ratio of the first quantity to the second quantity; and
adjust the first initial weight values of the plurality of pixels in the target image according to a preset weight adjustment value, to obtain the fusion weight values of the plurality of pixels in the target image.

### Claim 20 (depends on 19)

The image processing apparatus according to claim 19, wherein
the fusion weight value for each pixel of the plurality of pixels in the target image is equal to the first initial weight value of the respective pixel multiplied by the preset weight adjustment value.
