Selective Image Blurring via Shader Code and Masking

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing image processing applications for achieving a shallow depth of field (DOF) on mobile devices are computationally intensive and unsuitable for use on smartphones, making them inefficient for real-time image processing.

Innovation Solution

A computer system and method for selectively blurring portions of an image using shader code and a mask, allowing users to configure the mask via a touchscreen interface, which combines the original and blurred images to create a composite image with a shallow DOF effect, utilizing a blur engine, mask engine, and effects engine to generate a composite image with an unblurred and blurred portion.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If traditional post-processing techniques are used to achieve shallow depth of field, then the DOF effect is achieved, but the computational intensity becomes too high for mobile devices

Engineering Contradiction:

ImproveDOF effect qualityVSAvoidcomputational intensity

Core Design Contradiction:

ReliabilityVSUse of energy by moving object

Solution Approach 1:

The image processing is segmented into two passes: a first pass that processes only the background region to generate a blurred background, and a second pass that processes the foreground region. This segmentation reduces the total computational load compared to processing the entire image, while still achieving the desired shallow DOF effect.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The patent applies blurring processing selectively to only the background portion of the image rather than the entire image. By performing partial action on the background region that requires blurring, the computational intensity is reduced while maintaining the effectiveness of the shallow DOF effect in the final composite image.

Inventive Principle:

Principle #16Partial or excessive action

2Reliability

If existing image processing applications process the entire image, then the blurring effect is applied, but the processing time increases significantly

Engineering Contradiction:

Improveblurring effectVSAvoidprocessing time

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The image is divided into foreground and background regions, with blurring applied only to the background in the first pass. This segmentation strategy reduces processing time by avoiding redundant computations on the foreground region that does not require blurring, while still achieving the desired blurring effect in the final output.

Inventive Principle:

Principle #1Segmentation

3Reliability

If more expensive equipment is used, then shallow depth of field can be achieved, but the cost increases

Engineering Contradiction:

Improveshallow DOF effectVSAvoidequipment cost

Core Design Contradiction:

ReliabilityVSEase of manufacture

Solution Approach 1:

The patent replaces the mechanical/optical system (expensive camera equipment with physical aperture control) with a computational system (image processing algorithms). By using software-based image processing to simulate shallow DOF effects, the need for expensive specialized equipment is eliminated, making the technology accessible on standard mobile devices.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentUS10430075B2Image processing for introducing blurring effects to an image

Publication Date: 2019.10.01 META PLATFORMS INC

AI summary

Image processing includes: applying shader code to an original image to generate a blurred image version (BIV); obtaining a composite image that is generated based at least in part on the original image and the BIV, wherein the composite image is generated by: obtaining a mask that includes an unblurred region and a blurred region; applying the mask to combine the original image and the BIV to render a composite image that includes an unblurred portion comprising a portion of the original image corresponding to the unblurred region of the mask, and a blurred portion comprising a portion of the BIV corresponding to the blurred region of the mask; and outputting the composite image to be displayed.