Image Background Blurring via Confidence Maps and Reduced Computation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing image background blurring methods using large-size filter kernels result in high data computation amounts, leading to inefficient blur processing.
Innovation Solution
An image background blurring method and device that generates a background image based on a confidence map, determines a reduction factor according to the blurring degree, and performs blur processing using a small-size filter mask, reducing data computation and complexity.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Manufacturing precision
If a large-size filter kernel is used to filter and blur the background image, then the background blur effect is improved, but the data computation amount increases and processing efficiency deteriorates
Solution Approach 1:
The patent segments the background image into multiple regions based on depth information, applying different blur strengths to different regions. This allows the use of smaller filter kernels in most regions while maintaining the overall blur effect, thereby reducing computation amount and improving efficiency.
Solution Approach 2:
The patent applies different blur processing parameters to different regions of the background image based on their depth relative to the subject. Regions closer to the subject receive stronger blur while distant regions receive weaker blur, allowing optimization of filter kernel sizes for each region and reducing overall computation.
2Manufacturing precision
If a large-size filter kernel is used for background blurring, then the blur quality is improved, but the data computation amount and processing complexity increase
Solution Approach 1:
The patent dynamically adjusts the filter kernel size and blur strength based on the depth of different background regions. By making the processing parameters adaptive rather than fixed, the system can use smaller kernels for distant regions and larger kernels only when necessary, reducing overall complexity and computation.
Data Source
AI summary
An image background blurring method includes: obtaining an image to be blurred; performing identification processing on the image by an image semantic segmentation model in response to a target object confirmation instruction to obtain a confidence map indicating a target region of a target object in the image; generating a background image of the image according to the confidence map; performing blur processing on the background image in response to a blurring instruction including a blurring degree to obtain a blurred background image, wherein the blur processing includes determining a reduction factor according to the blurring degree and performing reduction processing on the background image according to the reduction factor; and merging the blurred background image and the image according to the confidence map to obtain a target image. The present application enhances blur processing efficiency by reducing a data computation amount during the blur processing.