US 12,456,171 B2
Image quality adjustment method and apparatus, device, and medium
Yineng Xiong, Beijing (CN)
Assigned to BEIJING ZITIAO NETWORK TECHNOLOGY CO., LTD., Beijing (CN)
Filed by Beijing Zitiao Network Technology Co., Ltd., Beijing (CN)
Filed on Dec. 14, 2023, as Appl. No. 18/540,532.
Application 18/540,532 is a continuation of application No. PCT/CN2022/112786, filed on Aug. 16, 2022.
Claims priority of application No. 202110950397.0 (CN), filed on Aug. 18, 2021.
Prior Publication US 2024/0127406 A1, Apr. 18, 2024
Int. Cl. G06T 5/60 (2024.01); G06T 7/00 (2017.01); G06V 20/40 (2022.01)
CPC G06T 5/60 (2024.01) [G06T 7/0002 (2013.01); G06V 20/41 (2022.01); G06V 20/46 (2022.01); G06V 20/49 (2022.01); G06T 2207/10016 (2013.01); G06T 2207/20081 (2013.01); G06T 2207/20084 (2013.01); G06T 2207/30168 (2013.01)] 11 Claims
OG exemplary drawing
 
1. An image quality adjustment method, comprising:
acquiring a multimedia resource, wherein the multimedia resource comprises a video or an image;
determining a scene detection result and an image quality detection result corresponding to the multimedia resource, wherein the scene detection result is used to indicate a semantic result of at least one dimension of the multimedia resource, and the image quality detection result is used to indicate image quality of the multimedia resource; and
determining an image quality enhancement strategy based on the scene detection result and the image quality detection result, and performing image quality enhancement processing on the multimedia resource according to the image quality enhancement strategy, wherein the image quality enhancement strategy comprises at least one image quality enhancement algorithm;
wherein in a case where the image quality enhancement strategy comprises a plurality of image quality enhancement algorithms, the plurality of image quality enhancement algorithms have an execution order;
wherein in a case where the multimedia resource is a video, determining the scene detection result and the image quality detection result corresponding to the multimedia resource comprises:
extracting a plurality of key frames from the multimedia resource; and
determining the scene detection result and the image quality detection result corresponding to the multimedia resource by detecting the plurality of key frames;
wherein extracting the plurality of key frames from the multimedia resource comprises:
dividing the multimedia resource into a plurality of video clips, wherein a similarity between two adjacent video clips is less than a preset threshold; and
extracting a plurality of key frames from each video clip among the plurality of video clips;
wherein determining the image quality enhancement strategy based on the scene detection result and the image quality detection result comprises:
determining the corresponding image quality enhancement strategy by using an algorithm branch decision tree, according to the scene detection result and the image quality detection result,
wherein the algorithm branch decision tree is a decision tree comprising a plurality of branch judgment strategies,
wherein determining the corresponding image quality enhancement strategy by using the algorithm branch decision tree comprises:
inputting the scene detection result and the image quality detection result into the algorithm branch decision tree, performing branch judgment one by one based on a preset execution order of the plurality of branch judgment strategies, determining the image quality enhancement algorithm corresponding to a current branch judgment result after each branch judgment strategy, and obtaining the image quality enhancement strategy comprising a combination of at least one image quality enhancement algorithm after judgment ends.