公开(公告)号：US11317109B2

公开(公告)日：2022-04-26

申请号：US16913583

申请日：2020-06-26

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Heechul Yang ,  Minsoo Park

IPC: H04B1/66 ,  H04N7/12 ,  H04N11/02 ,  H04N11/04 ,  H04N19/44 ,  H04N19/124 ,  H04N19/176 ,  H04N19/46 ,  H04N19/96

Abstract: Provided is an image decoding method including determining a predicted quantization parameter of a current quantization group determined according to at least one of block split information and block size information, determining a difference quantization parameter of the current quantization group, determining a quantization parameter of the current quantization group, based on the predicted quantization parameter and the difference quantization parameter of the current quantization group, and inverse quantizing a current block included in the current quantization group, according to the quantization parameter of the current quantization group.

公开(公告)号：US10825140B1

公开(公告)日：2020-11-03

申请号：US16826851

申请日：2020-03-23

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Heechul Yang ,  Jongseok Lee ,  Youngo Park ,  Kwangpyo Choi

IPC: G06T3/40 ,  G06N3/04 ,  G06F7/544

Abstract: Provided are methods and apparatus related to Artificial Intelligence (AI) downscaling and upscaling and techniques related to reducing artifact problems. Some embodiments include down-scaling an original image through a Deep Neural Network (DNN); generating, from the original image and based on frequency transform coefficients, artifact information representing a region in the first image including an artifact in the first image. Post-processing may be performed based on the artifact information to change pixels in the first image, thus reducing the effect of artifacts.

公开(公告)号：US10817990B1

公开(公告)日：2020-10-27

申请号：US16850411

申请日：2020-04-16

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Heechul Yang ,  Jongseok Lee ,  Youngo Park ,  Kwangpyo Choi

IPC: G06T3/40 ,  G06N3/04 ,  G06F7/544

Abstract: Provided are methods and apparatus related to Artificial Intelligence (AI) downscaling and upscaling and techniques related to reducing artifact problems. Some embodiments include down-scaling an original image through a Deep Neural Network (DNN); generating, from the original image and based on frequency transform coefficients, artifact information representing a region in the first image including an artifact in the first image. Post-processing may be performed based on the artifact information to change pixels in the first image, thus reducing the effect of artifacts.