Image processing method and apparatus, device, and computer-readable storage medium

Patent metadata

Field	Value
Publication number	US-2023222696-A1
Application number	US-202318184940-A
Country	US
Kind code	A1
Filing date	Mar 16, 2023
Priority date	Sep 17, 2020
Publication date	Jul 13, 2023
Grant date	—

Abstract

This application provides an image processing method and apparatus, a device, and a computer-readable storage medium for use in the field of computer vision. The image processing method includes the following steps: a first image device obtains a compressed image of a raw image and decompresses the compressed image to obtain a first decompressed image; the first image device determines target difference information based on difference information between the raw image and the first decompressed image; the first image device further compresses the target difference information to obtain compressed target difference information; and the first image device sends the compressed image and the compressed target difference information to a second image device. The second image device restores an image based on the received compressed image and target difference information. This application reduces a precision loss between the image restored by the second image device and the raw image.

First claim

What is claimed is:

1 . An image processing method, wherein the method comprises:
obtaining a compressed image of a raw image; decompressing the compressed image, to obtain a first decompressed image; determining target difference information based on difference information between the raw image and the first decompressed image; compressing the target difference information, to obtain compressed target difference information; and sending the compressed image and the compressed target difference information to a second image device.

2 . The method according to claim 1 , wherein the obtaining of the compressed image of the raw image comprises:
receiving or obtaining the raw image from a photographing apparatus; obtaining a reference image corresponding to the raw image; and compressing the raw image based on the reference image, to obtain the compressed image.

3 . The method according to claim 2 , wherein the method further comprises:
sending the reference image to the second image device.

4 . The method according to claim 1 , wherein both the difference information and the target difference information comprise an image matrix, and each image matrix comprises a plurality of image element values; and
the determining of the target difference information comprises: changing, to a preset value, an image element value that falls within a preset threshold range and that is in the image matrix comprised in the difference information, to obtain the image matrix comprised in the target difference information.

5 . The method according to claim 4 , wherein the obtaining of the compressed image of the raw image comprises:
receiving the raw image from a photographing apparatus; obtaining a reference image corresponding to the raw image; compressing the raw image based on the reference image, to obtain the compressed image; and sending the reference image to the second image device.

6 . The method according to claim 4 , wherein the obtaining of the compressed image of the raw image comprises:
obtaining the raw image through photographing; obtaining a reference image corresponding to the raw image; compressing the raw image based on the reference image, to obtain the compressed image; and sending the reference image to the second image device.

7 . An image processing method, wherein the method comprises:
receiving, from a first image device, a compressed image of a raw image and compressed target difference information; decompressing the compressed target difference information to obtain target difference information wherein the target difference information represents difference information between the raw image and a first decompressed image; decompressing the compressed image, to obtain the first decompressed image; and performing image processing on the first decompressed image based on the target difference information, to obtain a second decompressed image.

8 . The method according to claim 7 , wherein the method further comprises:
receiving, from the first image device, a reference image corresponding to the raw image.

9 . The method according to claim 8 , wherein both the target difference information and the first decompressed image comprise an image matrix, and each image matrix comprises a plurality of image element values; and
the performing of image processing on the first decompressed image based on the target difference information, to obtain the second decompressed image comprises: performing addition processing on the image matrix comprised in the first decompressed image and the image matrix comprised in the target difference information, to obtain an image matrix comprised in the second decompressed image; and determining the second decompressed image based on the image matrix comprised in the second decompressed image.

10 . The method according to claim 8 , wherein the decompressing of the compressed image, to obtain the first decompressed image comprises:
decompressing, based on the reference image, the compressed image, to obtain the first decompressed image.

11 . The method according to claim 10 , wherein both the target difference information and the first decompressed image comprise an image matrix, and each image matrix comprises a plurality of image element values; and
the performing of image processing on the first decompressed image based on the target difference information, to obtain a second decompressed image comprises:
performing addition processing on the image matrix comprised in the first decompressed image and the image matrix comprised in the target difference information, to obtain an image matrix comprised in the second decompressed image; and
determining the second decompressed image based on the image matrix comprised in the second decompressed image.

12 . An apparatus comprising a processor coupled with a memory storing computer instructions which, when executed by the processor, cause the processor to:
obtain a compressed image of a raw image; decompress the compressed image, to obtain a first decompressed image; determine target difference information, wherein the target difference information is obtained based on difference information between the raw image and the first decompressed image; compress the target difference information, to obtain compressed target difference information; and send the compressed image and the compressed target difference information to a second image device.

13 . The apparatus according to claim 12 , wherein both the difference information and the target difference information comprise an image matrix, and each image matrix comprises a plurality of image element values; and the instructions further cause the processor to:
change, to a preset value, an image element value that falls within a preset threshold range and that is in the image matrix comprised in the difference information, to obtain the image matrix comprised in the target difference information.

14 . The apparatus according to claim 12 , wherein the instructions further cause the processor to:
receive the raw image from a photographing apparatus; obtain a reference image corresponding to the raw image; and compress the raw image based on the reference image, to obtain the compressed image.

15 . The apparatus according to claim 12 , wherein the instructions further cause the processor to:
obtain the raw image through photographing; obtain a reference image corresponding to the raw image; and compress the raw image based on the reference image, to obtain the compressed image.

16 . The apparatus according to claim 14 , wherein the instructions further cause the processor to:
send the reference image to the second image device.

17 . An apparatus comprising a processor coupled with a memory storing computer instructions which, when executed by the processor, cause the processor to:
receive, from a first image device, a compressed image of a raw image and compressed target difference information; decompress the compressed target difference information to obtain target different information wherein the target difference information represents difference information between the raw image and a first decompressed image; decompress the compressed image, to obtain the first decompressed image; and perform image processing on the first decompressed image based on the target difference information, to obtain a second decompressed image.

18 . The apparatus according to claim 17 , wherein the instructions further cause the process

Assignees

• Huawei Tech Co Ltd

Inventors

• Zhou Kai
• Liu Hongbo

Classifications

• H04N19/137 Primary

  Motion inside a coding unit, e.g. average field, frame or block difference · CPC title

• H04N19/85 Primary

  using pre-processing or post-processing specially adapted for video compression · CPC title

• G06T9/00 Primary

  Image coding (bandwidth or redundancy reduction for static pictures H04N1/41; coding or decoding of static colour picture signals H04N1/64; methods or arrangements for coding, decoding, compressing or decompressing digital video signals H04N19/00) · CPC title

• H04N19/146

  Data rate or code amount at the encoder output · CPC title

• H04N19/147

  according to rate distortion criteria (rate-distortion as a criterion for motion estimation H04N19/567) · CPC title