Kernel prediction with kernel dictionary in image denoising
US11281970B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Nov 18, 2019 |
| Grant date | Mar 22, 2022 |
| Priority date | — |
| Expiry date | Jun 12, 2040 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06T2207/20084
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
Certain embodiments involve techniques for efficiently estimating denoising kernels for generating denoised images. For instance, a neural network receives a noisy reference image to denoise. The neural network uses a kernel dictionary of base kernels and generates a coefficient vector for each pixel in the reference image such that the coefficient vector includes a coefficient value for each base kernel in the kernel dictionary, where the base kernels are combined to generate a denoising kernel and each coefficient value indicates a contribution of a given base kernel to a denoising kernel. The neural network calculates the denoising kernel for a given pixel by applying the coefficient vector for that pixel to the kernel dictionary. The neural network applies each denoising kernel to the respective pixel to generate a denoised output image.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.