Methods, apparatuses, electronic devices, storage media, and products for determining image depth
By determining the image depth and distinguishing between foreground and background areas, the Deblur algorithm is used to deblur the background area, which solves the problem of artifacts in the foreground area during the image deblurring process and improves the image processing effect.
CN122089808APending Publication Date: 2026-05-26BEIJING XIAOMI MOBILE SOFTWARE CO LTD
View PDF 0 Cites 0 Cited by
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- BEIJING XIAOMI MOBILE SOFTWARE CO LTD
- Filing Date
- 2024-11-25
- Publication Date
- 2026-05-26
AI Technical Summary
Technical Problem
In the process of image deblurring, artifacts are prone to appear in the foreground area, which affects the image processing effect.
Method used
By determining the depth of the image and identifying the foreground region based on that depth, the Deblur algorithm is used to deblur the background region while preserving the foreground region, thus reducing the probability of artifacts.
Benefits of technology
It improves the effect of image deblurring and reduces the probability of artifacts appearing in the deblurred image.
✦ Generated by Eureka AI based on patent content.
Smart Images
Figure CN122089808A_ABST
Abstract
This disclosure relates to a method, apparatus, electronic device, storage medium, and product for determining image depth. The method includes: determining a first optical flow image corresponding to the first image based on a first image in a video and a previous frame image; adjusting the first optical flow values of multiple target pixels in the first optical flow image based on the posture information of the electronic device during the process from acquiring the previous frame image to acquiring the first image, to obtain second optical flow values; determining a near-field region in the first image based on the second optical flow values of the multiple target pixels; and deblurring the region in the first image excluding the near-field region to obtain a second image. The method of this disclosure can determine the near-field region in the first image, and by deblurring the region in the first image excluding the near-field region, the probability of artifacts appearing in the deblurred first image can be reduced, thereby improving the image processing effect.
Need to check novelty before this filing date? Find Prior Art