Samsung Electronics Co., Ltd.

Quockhanh Dinh

Kwangpyo Choi

Youngo Park

Minseok Choi

Jaehwan Kim

Jongseok Lee

Sunyoung Jeon

Minwoo Park

Minsoo Park

Yinji Piao

Kyungah Kim

Kyonghwan Jin

Jaeyeon Park

Yongsup Park

An image decoding method and apparatus obtain intra prediction feature data of a current block from a bitstream, determine an intra flow indicating a reference pixel of a current pixel in the current block, by applying the intra prediction feature data, neighboring pixels of the current block, and coding context information of the current block to a neural network, obtain a predicted pixel of the current pixel based on the intra flow of the current block, and reconstruct the current block based on the predicted pixel.

Image decoding apparatus and method and image encoding apparatus and method

A method of decoding an image, including obtaining a motion vector of a current block; obtaining a preliminary prediction block based on a reference block indicated by the motion vector in a reference image; obtaining a final prediction block for the current block by applying, to a neural network, at least one of a picture order count (POC) map including a POC difference between the reference image and a current image including the current block, the preliminary prediction block, and a quantization error map; and reconstructing the current block based on the final prediction block and a residual block obtained from a bitstream, wherein sample values of the quantization error map are calculated based on a quantization parameter for the reference block.

Method and apparatus for image decoding and image encoding using AI prediction block

A method of decoding an image based on cross-channel prediction using artificial intelligence (AI) includes obtaining cross-channel prediction information by applying feature data for cross-channel prediction to a neural-network-based cross-channel decoder, obtaining a predicted image of a chroma image by performing cross-channel prediction based on a reconstructed luma image and the cross-channel prediction information, obtaining a residual image of the chroma image by applying feature data of the chroma image to a neural-network-based chroma residual decoder, and reconstructing the chroma image based on the predicted image and the residual image.

Artificial intelligence-based image encoding apparatus and method and decoding apparatus and method

An image decoding method using artificial intelligence (AI), including obtaining, from a bitstream, a current optical flow and correction data which are generated based on a current predicted image and a current image; obtaining the current predicted image based on a previous reconstructed image and the current optical flow; obtaining feature data of the current predicted image by applying the current predicted image to a neural network-based predicted image encoder; and obtaining a current reconstructed image corresponding to the current image by applying the correction data and the feature data of the current predicted image to a neural network-based image decoder.

Image encoding apparatus and image decoding apparatus both using artificial intelligence, and image encoding method and image decoding method performed by the image encoding apparatus and the image decoding apparatus

An image processing method and an image processing apparatus are provided to obtain input data for deblocking filtering based on deblocking filtering target pixels of at least one line perpendicular to a boundary line of blocks and encoding information about the deblocking filtering target pixels of at least one line, obtain a feature map of the input data by inputting the input data to a first neural network, obtain a deblocking filter coefficient by inputting the feature map to a second neural network, obtain a deblocking filter compensation value by inputting the feature map to a third neural network, obtain a deblocking filter strength by inputting the input data to a fourth neural network, obtain deblocking filtered pixels by performing deblocking filtering on the deblocking filtering target pixels of the at least one line using the deblocking filter coefficient, the deblocking filter compensation value, and the deblocking filter strength.

Image processing method and apparatus using neural network based deblocking filtering

An image processing apparatus including a memory storing instructions, and a processor configured to operate based on the instructions to reconstruct a current block from encoded data of the current block, obtain a quantization error map including sample values calculated based on a quantization parameter included in the encoded data, obtain a first modified block by applying the current block and the quantization error map to a neural network, obtain a first differential block between the current block and the first modified block, obtain a second differential block by changing sample values of the first differential block based on a parameter dependent on a feature of the current block, and obtain a second modified block by combining the current block and the second differential block.

Apparatus and method for applying artificial intelligence-based filtering to image

An image processing apparatus, including a memory configured to store one or more instructions; and a processor configured to execute the one or more instructions stored in the memory to cause the image processing apparatus to: identify, in a previous frame, a prediction sample corresponding to a current sample of a current frame, generate a prediction frame for the current frame by changing a sample value of a collocated sample of the previous frame according to a sample value of the prediction sample, derive a weight by comparing a sample value of the current sample with the sample value of the prediction sample, apply the weight to a collocated sample of the prediction frame to obtain a weighted prediction frame, and obtain a current output frame by processing the current frame and the weighted prediction frame through a neural network comprising a convolution layer.

Image processing apparatus and method of processing multi-frames using the same

An image decoding method includes obtaining feature data of a current optical flow and feature data of a current residual image from a bitstream; obtaining the current optical flow and first weight data by applying the feature data of the current optical flow to an optical flow decoder; obtaining the current residual image by applying the feature data of the current residual image to a residual decoder; obtaining a preliminary prediction image from the previous reconstructed image, based on the current optical flow; obtaining a final prediction image by applying sample values of the first weight data to sample values of the preliminary prediction image; and obtaining a current reconstructed image corresponding to the current image by combining the final prediction image with the current residual image.

Device and method for encoding and decoding image using AI

A method includes obtaining, by a second processor of the electronic device, from a first processor of the electronic device, a control signal for obtaining image data, loading any one learning model of at least one learning model into a memory, obtaining, by using the camera module, raw image data of the object, from light reflected from the object, the raw image data being configured to have a specified color array consisting of a plurality of colors with respect to a plurality of pixels, obtaining, by using the loaded any one learning model, a color data set with respect to the plurality of pixels from the obtained raw image data, the color data set including a plurality of pieces of color data classified according to the plurality of colors, and obtaining the noise-reduced image data of the object by using the obtained color data set.

Method of generating noise-reduced image data and electronic device for performing the same

A method of reconstructing an optical flow by using artificial intelligence (AI), including obtaining, from a bitstream, feature data of a current residual optical flow for a current image; obtaining the current residual optical flow by applying the feature data of the current residual optical flow to a neural-network-based first decoder; obtaining a current predicted optical flow based on at least one of a previous optical flow, feature data of the previous optical flow, and feature data of a previous residual optical flow; and reconstructing a current optical flow based on the current residual optical flow and the current predicted optical flow.

Artificial intelligence-based image encoding and decoding apparatus and method

An image decoding method using artificial intelligence (AI), including obtaining feature data of a current optical flow and feature data of current differential data from a bitstream corresponding to a current image; obtaining the current optical flow by applying the feature data of the current optical flow to a neural-network-based first decoder; applying at least one of the feature data of the current optical flow and feature data of a previous optical flow to a first preprocessing neural network; obtain a first concatenation result by concatenating feature data obtained from the first preprocessing neural network with the feature data of the current differential data; obtaining the current differential data by applying the first concatenation result to a neural-network-based second decoder; and reconstructing the current image using the current differential data and a current predicted image generated from a previous reconstructed image based on the current optical flow.

Image encoding and decoding apparatus and method using artificial intelligence

An artificial intelligence (AI) decoding apparatus obtains image data corresponding to a first image, which is AI-downscaled from an original image by an AI encoding apparatus by using a first deep neural network (DNN); reconstructs a second image corresponding to the first image, based on the image data; and obtain a third image, which is AI-upscaled from the second image, convolution is performed based on the second image and second parameters of a filter kernel included in a second DNN, wherein each of the second parameters is an integer value, and the second parameters are determined as values associated with first parameters of a filter kernel included in the first DNN. Embodiments use memory-efficient values with respect to filter kernels. Parameters used to obtain the memory-efficient integer values may be obtained via joint training between the first DNN and the second DNN.

Artificial intelligence (AI) encoding apparatus and operating method thereof and AI decoding apparatus and operating method thereof

An artificial intelligence (AI) decoding apparatus includes a memory storing one or more instructions, and a processor configured to execute the stored one or more instructions, to obtain image data corresponding to a first image that is encoded, obtain a second image corresponding to the first image by decoding the obtained image data, determine whether to perform AI up-scaling of the obtained second image, based on the AI up-scaling of the obtained second image being determined to be performed, obtain a third image by performing the AI up-scaling of the obtained second image through an up-scaling deep neural network (DNN), and output the obtained third image, and based on the AI up-scaling of the obtained second image being determined to be not performed, output the obtained second image.

Apparatuses and methods for performing artificial intelligence encoding and artificial intelligence decoding on image

Provided is 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 stored in the memory, the processor is configured to: obtain AI data related to AI down-scaling an original image to a first image; obtain image data corresponding to an encoding result on the first image; obtain a second image corresponding to the first image by performing a decoding on the image data; obtain deep neural network (DNN) setting information among a plurality of DNN setting information from the AI data; and obtain, by an up-scaling DNN, a third image by performing the AI up-scaling on the second image, the up-scaling DNN being configured with the obtained DNN setting information, wherein the plurality of DNN setting information comprises a parameter used in the up-scaling DNN, the parameter being obtained through joint training of the up-scaling DNN and a down-scaling DNN, and wherein the down-scaling DNN is used to obtain the first image from the original image.

Methods and apparatuses for performing artificial intelligence encoding and artificial intelligence decoding on image

Proposed are a method and apparatus for evaluating the quality of an image, the method including obtaining blocks each having a predetermined size by splitting a target image for evaluating a quality and a reference image that is to be compared with the target image, determining sensitivity information and quality assessment information of each of the blocks by inputting the blocks to a video quality assessment network, and determining a final image quality assessment score of the target image by combining the pieces of quality assessment information of the blocks with each other, based on the pieces of sensitivity information of the blocks.

Growing community of inventors

Suwon-si, South Korea

Quockhanh Dinh