Samsung electronics co., ltd. (20240177278). Restoring Images Using Deconvolution simplified abstract

Restoring Images Using Deconvolution

Organization Name

samsung electronics co., ltd.

Inventor(s)

Changgeng Liu of San Jose CA (US)

Luxi Zhao of Toronto (CA)

Ziwen Jiang of Sunnyvale CA (US)

Abdelrahman Abdelhamed of Toronto (CA)

Abhijith Punnappurath of North York (CA)

Ye Zhao of Sunnyvale CA (US)

Ernest Rehmatulla Post of San Francisco CA (US)

Michael Brown of Toronto (CA)

Sajid Sadi of San Jose CA (US)

Restoring Images Using Deconvolution - A simplified explanation of the abstract

This abstract first appeared for US patent application 20240177278 titled 'Restoring Images Using Deconvolution

Simplified Explanation

The method described in the abstract involves generating deconvolved image patches from an accessed image by applying a set of point-spread functions (psfs) to each patch, determining weights for each portion of the image patch, and then interpolating the deconvolved image patches based on these weights to generate a restored image patch.

• Accessing an image and generating image patches
• Applying a set of point-spread functions (psfs) to each image patch for deconvolution
• Determining weights for each portion of the image patch
• Interpolating deconvolved image patches based on the set of weights

Potential Applications

This technology could be applied in image processing, medical imaging, and computer vision applications where image restoration and enhancement are required.

Problems Solved

This technology helps in improving the quality of images by deconvolving image patches and interpolating them to generate a restored image patch with enhanced details and clarity.

Benefits

The benefits of this technology include improved image quality, enhanced details, and better visualization in various applications such as medical imaging and computer vision.

Potential Commercial Applications

Potential commercial applications of this technology include software development for image processing, medical imaging equipment, and computer vision systems.

Possible Prior Art

One possible prior art in this field is the use of convolutional neural networks for image deconvolution and restoration, which has been a popular approach in recent years.

What are the limitations of this technology in real-world applications?

The limitations of this technology in real-world applications may include computational complexity, the need for high-quality input images, and potential artifacts in the restored images.

How does this technology compare to existing image restoration techniques?

This technology offers a unique approach to image restoration by deconvolving image patches with a set of point-spread functions and interpolating the results based on weights, which may provide more detailed and accurate restoration compared to traditional techniques.

Original Abstract Submitted

in one embodiment, a method includes generating, from an accessed image, one or more image patches, and for each image patch: (1) accessing a set of point-spread functions (psfs), wherein each psf in the set of psfs corresponds to one of a plurality of points in the image patch; (2) generating a set of deconvolved image patches by deconvolving the image patch with each psf from the set of psfs for that patch; (3) determining, for each of one or more portions of the image patch, a set of weights, wherein each weight in the set of weights is associated with one of the deconvolved image patches; and (4) generating a restored image patch by interpolating the set of deconvolved image patches based on the set of weights.