Multi-Camera Image Fusion for Sharp, Full-Frame Stabilization

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing image anti-shake technologies reduce image sharpness and frame during video shooting due to edge cropping, which affects the video shooting effect.

Innovation Solution

Fusing images captured by two cameras with different field of views to perform image shake correction, using electronic image stabilization algorithms, and compensating for frame loss by enlarging the cropped image while improving sharpness through image fusion.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Stability of the object's composition

If image shake correction is performed using existing anti-shake technology, then image stability is improved, but image sharpness and frame size are reduced

Engineering Contradiction:
Improveimage stabilityVSAvoidimage sharpness
Core Design Contradiction:
Stability of the object's compositionVSManufacturing precision

Solution Approach 1:

The patent merges images from multiple cameras with different field of views to create a fused image. This fusion process combines the advantages of each camera: wide-angle coverage from one camera and high sharpness from another camera, thereby maintaining both image stability and sharpness during shake correction.

Inventive Principle:
Principle #5Merging (Combining)

Solution Approach 2:

The patent introduces a new dimension by using multiple cameras with different field of views simultaneously. Instead of relying on a single camera's image, the system fuses images from different dimensional perspectives (different FOVs) to achieve both stability and sharpness in the final output.

Inventive Principle:
Principle #17Another dimension (Dimensionality change)

2Stability of the object's composition

If image shake correction is performed using existing anti-shake technology, then image stability is improved, but frame size is reduced

Engineering Contradiction:
Improveimage stabilityVSAvoidframe size
Core Design Contradiction:
Stability of the object's compositionVSArea of stationary object

Solution Approach 1:

The patent merges images from multiple cameras with different field of views to create a fused image. This fusion process combines the advantages of each camera: wide-angle coverage from one camera and high sharpness from another camera, thereby maintaining both image stability and sharpness during shake correction.

Inventive Principle:
Principle #5Merging (Combining)

Solution Approach 2:

The patent introduces a new dimension by using multiple cameras with different field of views simultaneously. Instead of relying on a single camera's image, the system fuses images from different dimensional perspectives (different FOVs) to achieve both stability and sharpness in the final output.

Inventive Principle:
Principle #17Another dimension (Dimensionality change)

3Stability of the object's composition

If edge cropping is applied during image shake correction, then shake compensation is achieved, but image quality deteriorates

Engineering Contradiction:
Improveshake compensationVSAvoidimage quality
Core Design Contradiction:
Stability of the object's compositionVSManufacturing precision

Solution Approach 1:

The patent converts the harmful effect of edge cropping into a benefit by using the cropped regions from different cameras to create a fused image. The cropping process is reframed as a selective combination process where the strengths of different camera images are merged to produce higher quality output than any single input image.

Inventive Principle:
Principle #22Blessing in disguise (Convert harm into benefit)

Data Source

PatentEP4064176B1Image processing method and apparatus, storage medium and electronic device
Publication Date: 2025.08.27 REALME CHONGQING MOBILE TELECOMM CORP LTD
  • EP4064176B1 patent drawingFigure 1~3
  • EP4064176B1 patent drawingFigure 4~6
  • EP4064176B1 patent drawingFigure 7

AI summary

The present disclosure provides an image processing method and apparatus, an electronic device, and a storage medium, and relates to the technical field of image processing. The method includes: obtaining a first image captured by a first camera and a second image captured by a second camera respectively, the first camera and the second camera having different field of view; and determining a fused image based on the first image and the second image; obtaining an output image by performing image shake correction on the fused image. The present disclosure can improve the sharpness of the image and increase the frame of the image.