Model training and image processing method and device, electronic equipment and storage medium
By sampling and evaluating each frame of a high-resolution video using a neural network, a sequence of image frames with the same resolution but smaller size is generated. This solves the problem of low efficiency in high-resolution video quality assessment, improving both accuracy and efficiency while maintaining video quality.
CN116343094BActive Publication Date: 2026-05-26SENSETIME INT PTE LTD +1
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- SENSETIME INT PTE LTD
- Filing Date
- 2023-03-31
- Publication Date
- 2026-05-26
Smart Images
Figure CN116343094B_ABST
Abstract
This disclosure provides a model training and image processing method, apparatus, electronic device, and storage medium. The image processing method includes: determining at least one first image frame sequence based on a video to be processed, each first image frame sequence including at least one first image frame; for each first image frame sequence, determining a second image frame sequence based on the first image frame sequence, wherein each second image frame in the second image frame sequence corresponds to a first image frame in the first image frame sequence, and at least one first pixel block in each second image frame is obtained by sampling at least one first image block in the corresponding first image; determining first quality information for each second image frame sequence; and determining second quality information for the video to be processed based on each first quality information.
Need to check novelty before this filing date? Find Prior Art