Back to results
US 11,694,306 B2Granted
Image processing apparatus and method of operating the same
AssigneeSamsung Electronics Co., Ltd.
InventorsSangwook Baek, Yongsup Park, Sangmi Lee, Youngo Park, Kwangpyo Choi
Life of this patent
Estimating the term…
Abstract
An image processing apparatus for performing image quality processing on an image includes a feature extraction network and an image quality processing network including one or more modulation blocks, wherein each of the one or more modulation blocks includes a convolution layer, a modulation layer, and an activation layer for processing the image.
Claims20
An image processing apparatus comprising:
- a memory storing one or more instructions;
- and
- a processor configured to execute the one or more instructions stored in the memory to:
- extract feature information of an input image by using a feature extraction network;
- and
- generate an output image by processing the input image, by using an image quality processing network comprising one or more modulation blocks, wherein each modulation block among the one or more modulation blocks comprises:
- a convolution layer configured to perform a convolution operation between an input to the convolution layer and a kernel in the convolution layer and output a feature map based on the convolution operation,
- a modulation layer arranged to receive the feature map output from the convolution layer as input and generate a modulated feature map by modulating the feature map based on the feature information of the input image;
- and
- an activation layer arranged to receive the modulated feature map and generate an output by applying an activation function to the modulated feature map.
7 more elements
A method of operating an image processing apparatus, the method comprising:
- extracting feature information of an input image using a feature extraction network;
- and
- generating an output image by processing the input image, by using an image quality processing network comprising one or more modulation blocks, wherein each modulation block among the one or more modulation blocks comprises:
- a convolution layer performing a convolution operation between an input to the convolution layer and a kernel in the convolution layer and output a feature map based on the convolution operation,
- a modulation layer receiving the feature map output from the convolution layer as input and generating a modulated feature map by modulating the feature map based on the feature information of the input image;
- and
- an activation layer receiving the modulated feature map and generating an output by applying an activation function to the modulated feature map.
4 more elements
Dependencies are inferred from the claim text.