Dynamic Weight Map for Image Deblurring
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing image processing methods for deblurring images fail to effectively suppress side effects like edge fall and ringing, especially around luminance saturated areas, and these effects vary with image brightness and scene conditions.
Innovation Solution
An image processing method that generates a weight map based on brightness and scene information of the captured image, as well as information about saturated areas, to obtain a weighted mean of the captured image and the deblurred image, thereby maintaining a proper deblurring effect while reducing side effects.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Object-affected harmful factors
If a weighted mean of the captured image and deblurred image is obtained using fixed weights based on saturated areas, then side effects like ringing are reduced in bright images, but the correction effect is reduced too much in dark images
Solution Approach 1:
The weight map is made dynamic by adjusting weights based on the average brightness of the captured image. In bright images, higher weights are assigned to suppress side effects around saturated areas, while in dark images, lower weights preserve the correction effect. This dynamic adaptation resolves the contradiction between suppressing harmful side effects and maintaining correction effectiveness across different brightness conditions.
Solution Approach 2:
The invention changes the weight parameters of the weighted mean operation based on the brightness parameter of the input image. By modifying the weight values according to image brightness, the system adapts the degree of correction applied, thereby balancing side effect suppression with correction effectiveness for different scene conditions.
2Manufacturing precision
If deblurring is performed strongly to correct optical aberration, then blur correction effect is improved, but side effects like edge fall and ringing become more conspicuous
Solution Approach 1:
The invention applies local quality by using a weight map where different weights are assigned to different regions of the image. Areas around saturated pixels receive higher weights to suppress side effects, while other areas maintain lower weights to preserve correction effects. This localized weight application allows strong deblurring where needed while suppressing artifacts in critical regions.
Data Source
AI summary
An image processing method includes acquiring a captured image obtained by imaging, generating a first image by correcting a blur component of the captured image, and generating a second image based on the captured image, the first image, and weight information. The weight information is generated based on (i) information on brightness of the captured image or information on a scene of the captured image and (ii) information on a saturated area in the captured image.