Back to results
US 10,706,504 B2Granted
Image processing methods and image processing devices
AssigneeBoe Technology Group Co., Ltd.
InventorsHanwen Liu, Pablo Navarrete Michelini
Life of this patent
Estimating the term…
Abstract
The embodiments of the present disclosure provide an image processing method, and a processing device. The image processing method comprises: acquiring a first image including N components, where N is a positive integer greater than or equal to 1; and performing image conversion processing on the first image using a generative neural network, to output a first output image, wherein the generative neural network is trained using a Laplace transform function.
Claims14
An image processing method, comprising:
- acquiring a first image including N components, where N is an integer greater than or equal to 1;
- and
- performing image conversion processing on the first image using a generative neural network, to output a first output image,
- wherein the generative neural network is trained using a Laplace transform function,
- wherein performing image conversion processing on the first image using a generative neural network comprises:
- performing image conversion processing on the first image using the generative neural network based on an input image including the first image and a first noise image.
3 more elements
An image processing device, comprising:
- one or more processors;
- and
- one or more memories connected to the one or more processors and having computer readable codes stored thereon, which when being executed by the one or more processors, cause the one or more processors to be configured to:
- perform image conversion processing on a first image including N components using a generative neural network, to output a first output image, where N is an integer greater than or equal to 1,
- wherein the generative neural network is trained using a Laplace transform function;
- and
- wherein performing image conversion processing on the first image using a generative neural network comprises:
- performing image conversion processing on the first image using the generative neural network based on an input image including the first image and a first noise image,
- wherein the first noise image comprises M components, where M is an integer greater than or equal to 1.
6 more elements
Dependencies are inferred from the claim text.