Samsung Electronics Co., Ltd.

Sangjo Lee

Doohyun Kim

Daesung Cho

Sangkwon Na

Shihwa Lee

Wooshik Kim

Taejun Park

Hyeyun Kim

Dmitri Birinov

Jihun Kim

Jaesung Park

Bongjoe Kim

Kyuha Choi

Hyeyeon Chung

Minyong Sung

Dohyung Kim

Seungho Park

Seungwoo Lee

Hongki Kwon

Kiwon Yoo

Woochul Kim

Byoung-Ju Song

Deoksoo Park

Daeeun Kim

Junghyun Lim

JongSeon Kim

SangHoon Ha

Shinwa Lee

Bomyun Kim

Disclosed are a display apparatus and a method of controlling the same, the display apparatus including: a video decoder configured to decode a video signal; and an artificial intelligence (AI) scaler including a plurality of filters provided to make an output of a certain filter be used as an input of another filter, and configured to control a resolution of an image by processing the decoded video signal, each of the plurality of filters being selectively turned on or off based on a control signal, the filter being turned on processing the video signal based on a parameter set by learning, and the filter being turned off bypassing and outputting the input video signal.

Display apparatus and method of controlling the same using artificial intelligence (AI)

The disclosure relates to an artificial intelligence (AI) system that uses a machine learning algorithm and an application thereof. A method for controlling an electronic apparatus according to the disclosure includes receiving image data and information associated with a filter set that is applied to an artificial intelligence model for upscaling the image data from an external server; decoding the image data; upscaling the decoded image data using a first artificial intelligence model that is obtained based on the information associated with the filter set; and providing the upscaled image data for output.

Apparatus and method with artificial intelligence for scaling image data

An image processing apparatus includes: a memory storing one or more instructions; and a processor by executing the one or more instructions stored in the memory is configured to: extract a first image feature from a first image; search for, based on a transmission characteristic of the first image and the first image feature, a first cluster corresponding to the first image from among a plurality of clusters stored in the image processing apparatus, each cluster including a representative image feature and a representative image quality parameter; perform image quality processing on the first image based on a first representative image quality parameter in the first cluster; obtain, based on the first image that has undergone the image quality processing, a first update parameter obtained by updating the first representative image quality parameter; and update the plurality of clusters based on the first update parameter.

Image processing apparatus and operation method thereof

An artificial intelligence (AI) encoding apparatus includes at least one processor configured to: determine a downscaling target, based on a target resolution for a first image, obtain the first image by AI-downscaling an original image using an AI-downscaling neural network corresponding to the downscaling target, generate image data by encoding the first image, select AI-upscaling neural network set identification information, based on the target resolution of the first image, characteristic information of the original image, and a target detail intensity, generate AI data including the target resolution of the first image, bit depth information of the first image, the AI-upscaling neural network set identification information, and encoding control information, and generate AI encoding data including the image data and the AI data; and a communication interface configured to transmit the AI encoding data to an AI decoding apparatus, wherein the AI data includes information about an AI-upscaling neural network corresponding to the AI-downscaling neural network.

AI encoding apparatus and operation method of the same, and AI decoding apparatus and operation method of the same

Display apparatus and method of controlling the same

An artificial intelligence (AI) processor includes at least one memory; a plurality of neural network operators comprising circuitry configured to process an image; and a controller configured to control the at least one memory and the plurality of neural network operators. The controller controls input image data of an image to be stored in the at least one memory and controls at least one of the plurality of neural network operators to perform a neural network operation on image data split based on a size of the image and data processing capabilities of the plurality of neural network operators, and output upscaled image data.

Artificial intelligence processor and method of performing neural network operation thereof

A method for controlling an electronic apparatus according to the disclosure includes receiving image data and information associated with a filter set that is applied to an artificial intelligence model for upscaling the image data from an external server; decoding the image data; upscaling the decoded image data using a first artificial intelligence model that is obtained based on the information associated with the filter set; and providing the upscaled image data for output.

Electronic apparatus and method for upscaling a down-scaled image by selecting an improved filter set for an artificial intelligence model

Disclosed are a display apparatus, an image providing apparatus, and methods of controlling the same, the display apparatus including: a display; and a processor configured to: decode an encoded video stream, decompress the video stream through a neural network including a plurality of channels and a plurality of layers with a parameter set based on learning, and perform image compensation determined based on learning about the decompression with respect to the video stream.

Display apparatus, image providing apparatus, and methods of controlling the same

Provided is a filtering apparatus, method, and medium for a multi-format codec, in which a blocking artifact of decoded video data is removed. The filtering apparatus includes a compression format detection unit, a block strength determination unit, a table determination unit, and a first filtering unit. The compression format detection unit detects a video compression format of the decoded video data. The block strength determination unit determines a block strength indicating a filtering strength with respect to the decoded video data according to the detected video compression format. The table determination unit determines a filtering table differently according to the block strength when the block strength is greater than a predetermined threshold. The first filtering unit performs filtering on the decoded video data in units of a block using the determined filtering table.

Filtering apparatus, method, and medium for multi-format codec

A memory mapping apparatus and a method in a video decoder/encoder utilize a dividing unit, a storage unit and a memory allocation unit. The dividing unit divides picture data into macroblocks and divides each of the macroblocks, which are units of encoding, into partitions having a predetermined size. A storage unit comprises at least one memory bank which is independently accessible. A memory allocation unit allocates adjacent partitions to different memory banks. Accordingly, a total number of cycles necessary to read and write the picture data is reduced.

Memory mapping apparatus and method for video decoder/encoder

In an image data processing device, a selection unit receives a block of original image data of a current image, a block of compressed and reconstructed image data of the current image, and a block of compressed and reconstructed data of a previous image that precedes the current image. A comparison unit compares the block of compressed and reconstructed image data of the current image with the block of compressed and reconstructed data of the previous image. An output unit, in the event that the comparison of the comparison unit results in a match, outputs the block of original image data of the current image as first output data, and, in the event that the comparison of the comparison unit does not result in a match, outputs the block of compressed and reconstructed data of the previous image as the first output data.

Device and method of processing image data to be displayed on a display device

A method, medium, and apparatus controlling a bit rate in image data encoding. The method for controlling a bit rate in image data encoding includes setting a reference bit amount for encoding a block group composed of a predetermined number of blocks created by dividing image data of a frame, encoding pixel values of the blocks according to a bit depth used to quantize the pixel values of the blocks, checking whether encoding of the frame is completed, and comparing a group bit amount indicating the amount of encoded bits of the block group with the set reference bit amount to adjust the bit depth if encoding of the unit frame is not completed and accordingly repeating the setting of the reference bit amount, encoding pixel values of the blocks, and checking whether encoding of the frame is completed.

Method, medium, and apparatus controlling bit rate in image data encoding

An apparatus and method for writing and/or reading data in an image processing system are provided. The apparatus for writing data includes: a memory formed with at least one or more banks capable of being accessed independently; and a memory control unit controlling so that a luminance component, a first chrominance component and a second chrominance component belonging to one macroblock are written based on respective structures different to each other, in the memory. The apparatus for reading data includes: a memory formed with one or more banks capable of being accessed independently in which a luminance component, a first chrominance component, and a second chrominance component belonging to one macroblock are written based on respective structures different to each other, in each bank of the memory; and a memory control unit controlling so that a luminance component, a first chrominance component, and a second chrominance component required are read from the memory.

Growing community of inventors

Suwon-si, South Korea

Sangjo Lee