Intel corporation (20240127408). ADAPTIVE DEFORMABLE KERNEL PREDICTION NETWORK FOR IMAGE DE-NOISING simplified abstract

ADAPTIVE DEFORMABLE KERNEL PREDICTION NETWORK FOR IMAGE DE-NOISING

Organization Name

intel corporation

Inventor(s)

Anbang Yao of Beijing 11 (CN)

Ming Lu of Beijing 11 (CN)

Yikai Wang of Beijing (CN)

Xiaoming Chen of Shanghai 31 (CN)

Junjie Huang of Shenzhen (CN)

Tao Lv of Shanghai (CN)

Yuanke Luo of Shanghai (CN)

Yi Yang of Shanghai 31 (CN)

Feng Chen of Shanghai 31 (CN)

Zhiming Wang of Shanghai 31 (CN)

Zhiqiao Zheng of Shenzhen (CN)

Shandong Wang of Beijing 11 (CN)

ADAPTIVE DEFORMABLE KERNEL PREDICTION NETWORK FOR IMAGE DE-NOISING - A simplified explanation of the abstract

This abstract first appeared for US patent application 20240127408 titled 'ADAPTIVE DEFORMABLE KERNEL PREDICTION NETWORK FOR IMAGE DE-NOISING

Simplified Explanation

The adaptive deformable kernel prediction network for image de-noising is a method that uses a convolutional neural network to filter pixels in an image and obtain a de-noised image.

• The method involves generating convolutional kernels with kernel values for each pixel, generating offsets for each pixel to indicate deviations from the pixel position, determining deviated pixel positions based on the offsets, and filtering the pixel with the convolutional kernel and pixel values of the deviated pixel positions to de-noise the image.

• • Potential Applications:**

- Image processing - Computer vision - Medical imaging

• • Problems Solved:**

- Image noise reduction - Enhancing image quality - Improving image analysis accuracy

• • Benefits:**

- Better image quality - Enhanced image processing capabilities - Improved accuracy in image analysis

• • Potential Commercial Applications:**

- Photography software - Medical imaging devices - Security systems

• • Possible Prior Art:**

One possible prior art in this field is the use of traditional image de-noising algorithms such as median filtering, Gaussian filtering, and wavelet denoising.

• • Unanswered Questions:**

1. How does the adaptive deformable kernel prediction network compare to other image de-noising techniques in terms of computational efficiency? 2. Are there any limitations to the adaptive deformable kernel prediction network in handling different types of image noise?

Original Abstract Submitted

embodiments are generally directed to an adaptive deformable kernel prediction network for image de-noising. an embodiment of a method for de-noising an image by a convolutional neural network implemented on a compute engine, the image including a plurality of pixels, the method comprising: for each of the plurality of pixels of the image, generating a convolutional kernel having a plurality of kernel values for the pixel; generating a plurality of offsets for the pixel respectively corresponding to the plurality of kernel values, each of the plurality of offsets to indicate a deviation from a pixel position of the pixel; determining a plurality of deviated pixel positions based on the pixel position of the pixel and the plurality of offsets; and filtering the pixel with the convolutional kernel and pixel values of the plurality of deviated pixel positions to obtain a de-noised pixel.