Samsung Electronics Co., Ltd.

Heechul Yang

Minsoo Park

Youngo Park

Kwangpyo Choi

Jaehwan Kim

Jongseok Lee

Inhak Na

Chaeeun Lee

Hyunkwon Chung

Minwoo Park

An artificial intelligence (AI) encoding apparatus includes a memory storing one or more instructions, and a processor configured to execute the one or more instructions stored in the memory to identify an object region of interest in an original image, obtain, from the original image, a plurality of original part images respectively including the object region of interest and a non-interest region, obtain a plurality of first images by performing AI scaling on the plurality of original part images through a scaling neural network (NN) that is configured to operate with NN setting information selected from among a plurality of pieces of NN setting information, at least based on whether the plurality of original part images include the object region of interest or the non-interest region, generate image data by encoding the plurality of first images, and transmit the image data, and AI data including information related to the AI scaling.

Artificial intelligence (AI) encoding apparatus and method and AI decoding apparatus and method for region of object of interest in image

An artificial intelligence (AI) decoding apparatus includes a memory storing one or more instructions; and a processor configured to execute the one or more instructions to obtain image data generated through first encoding on a first image; obtain a second image corresponding to the first image by performing first decoding on the image data; perform pre-processing of changing a resolution of the second image, according to a pre-determined output resolution; and obtain a fourth image having the pre-determined output resolution by applying AI up-scaling based on an up-scaling deep neural network (DNN) to a third image obtained as a result of the pre-processing.

Apparatus and method for performing artificial intelligence encoding and artificial intelligence decoding on image by using pre-processing

A method, performed by a terminal, of performing artificial intelligence (AI) decoding, including obtaining, based on a first image, image feature information of the first image, the image feature information being related to an image quality degradation; obtaining, based on the image feature information of the first image, neural network (NN) setting information of a first NN, from among NN setting information of a plurality of first NNs which are pre-stored and which correspond to a plurality of image quality degradation types; and obtaining, by using the first NN, a second image in which the image quality degradation is reduced.

Apparatus and method for performing artificial intelligence encoding and artificial intelligence decoding of image

A video decoding method includes: determining a largest size of a coding unit and a smallest size of the coding unit by using information about the largest size of the coding unit and information about the smallest size of the coding unit, the information being obtained from a bitstream; obtaining, from the bitstream, information about a largest size of a block allowed to be ternary split and information about a smallest size of the block allowed to be ternary split, determining the largest size of the block allowed to be ternary split, determining the smallest size of the block allowed to be ternary split, determining whether to ternary split a current block, and decoding blocks generated by ternary splitting the current block.

Video encoding method and apparatus, and video decoding method and apparatus using blocks split in various shapes from images

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.

Encoding method and apparatus therefor, and decoding method and apparatus therefor

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.

Growing community of inventors

Suwon-si, South Korea

Heechul Yang