公开(公告)号：US20210049741A1

公开(公告)日：2021-02-18

申请号：US16991689

申请日：2020-08-12

Applicant: Electronics and Telecommunications Research Institute

Inventor： Seok Bong YOO ,  Mi Kyong HAN

IPC: G06T3/40 ,  G06N3/04

Abstract: A method for generating a super resolution image may comprise up-scaling an input low resolution image; determining a directivity for each patch included in the up-scaled image; selecting an orientation-specified neural network or an orientation-non-specified neural network according to the directivity of the patch; applying the selected neural network to the patch; and obtaining a super resolution image by combining one or more patches output from the orientation-specified neural network and the orientation-non-specified neural network.

公开(公告)号：US20210042887A1

公开(公告)日：2021-02-11

申请号：US16987027

申请日：2020-08-06

Applicant: Electronics and Telecommunications Research Institute

Inventor： Seok Bong YOO ,  Mi Kyong HAN

IPC: G06T5/00 ,  G06T5/10 ,  G06T5/50 ,  G06N3/08 ,  G06N3/04

Abstract: A method for removing compressed Poisson noises in an image, based on deep neural networks, may comprise generating a plurality of block-aggregation images by performing block transform on low-frequency components of an input image; obtaining a plurality of restored block-aggregation images by inputting the plurality of block-aggregation images into a first deep neural network; generating a low-band output image from which noises for the low-frequency components are removed by performing inverse block transform on the plurality of restored block-aggregation images; and generating an output image from which compressed Poisson noises are removed by adding the low-band output image to a high-band output image from which noises for high-frequency components of the input image are removed.