Electronics and Telecommunications Research Institute

Jin-Wuk Seok

Hui-Yong Kim

Jin-Soo Choi

Youn-Hee Kim

Seung-Hyun Cho

Jong-Ho Kim

Se-Yoon Jeong

Woong Lim

Joo-Young Lee

Dae-Yeol Lee

Hyunsuk Ko

Je-Won Kang

Na-Young Kim

Seung-Kwon Beack

Seon-Tae Kim

Yong-Ki Son

Ji-Young Kwak

Pyeong-Soo Mah

Kyung-Hee Lee

Jae-Bok Park

Chang-Sik Cho

Hyun-Woo Cho

Myung-Seok Ki

Bum-Ho Kim

Hong-Soog Kim

Jung-Kyung Lee

Disclosed herein are a neural network model deployment method and apparatus for providing a deep learning service. The neural network model deployment method may include providing a specification wizard to a user, searching for and training a neural network based on a user requirement specification that is input through the specification wizard, generating a neural network template code based on the user requirement specification and the trained neural network, converting the trained neural network into a deployment neural network that is usable in a target device based on the user requirement specification, and deploying the deployment neural network to the target device.

Neural network model deployment method and apparatus for providing deep learning service

Disclosed herein are a method and apparatus for compressing learning parameters for training of a deep-learning model and transmitting the compressed parameters in a distributed processing environment. Multiple electronic devices in the distributed processing system perform training of a neural network. By performing training, parameters are updated. The electronic device may share the updated parameter thereof with additional electronic devices. In order to efficiently share the parameter, the residual of the parameter is provided to the additional electronic devices. When the residual of the parameter is provided, the additional electronic devices update the parameter using the residual of the parameter.

Method and device for providing compression and transmission of training parameters in distributed processing environment

A method and apparatus for image compression using a latent variable are provided. The multiple components of the latent variable may be sorted in order of importance. Through sorting, when the feature information of only some of the multiple components is used, the quality of a reconstructed image may be improved. In order to generate a latent variable, the components of which are sorted in order of importance, learning may be performed in various manners. Also, less important information may be eliminated from the latent variable, and processing, such as quantization, may be applied to the latent variable. Through elimination and processing, the amount of data for the latent variable may be reduced.

Method and device for compressing image and neural network using hidden variable

Disclosed herein is a context-adaptive entropy model for end-to-end optimized image compression. The entropy model exploits two types of contexts. The two types of contexts are a bit-consuming context and a bit-free context, respectively, and these contexts are classified depending on the corresponding context requires the allocation of additional bits. Based on these contexts, the entropy model may more accurately estimate the distribution of each latent representation using a more generalized form of entropy models, thus improving compression performance.

Method and apparatus for image processing using context-adaptive entropy model

Disclosed herein are a method and apparatus for measuring video quality based on a perceptually sensitive region. The quality of video may be measured based on a perceptually sensitive region and a change in the perceptually sensitive region. The perceptually sensitive region includes a spatial perceptually sensitive region, a temporal perceptually sensitive region, and a spatio-temporal perceptually sensitive region. Perceptual weights are applied to a detected perceptually sensitive region and a change in the detected perceptually sensitive region. Distortion is calculated based on the perceptually sensitive region and the change in the perceptually sensitive region, and a result of quality measurement for a video is generated based on the calculated distortion.

Method and apparatus for measuring video quality based on detection of change in perceptually sensitive region

Disclosed herein are a method and apparatus for video decoding and a method and apparatus for video encoding. A prediction block for a target block is generated by predicting the target block using a prediction network, and a reconstructed block for the target block is generated based on the prediction block and a reconstructed residual block. The prediction network includes an intra-prediction network and an inter-prediction network and uses a spatial reference block and/or a temporal reference block when it performs prediction. For learning in the prediction network, a loss function is defined, and learning in the prediction network is performed based on the loss function.

Image encoding and decoding method and device using prediction network

An inter-prediction method and apparatus uses a reference frame generated based on deep learning. In the inter-prediction method and apparatus, a reference frame is selected, and a virtual reference frame is generated based on the selected reference frame. A reference picture list is configured to include the generated virtual reference frame, and inter prediction for a target block is performed based on the virtual reference frame. The virtual reference frame may be generated based on a deep-learning network architecture, and may be generated based on video interpolation and/or video extrapolation that use the selected reference frame.

Inter-prediction method and apparatus using reference frame generated based on deep learning

Disclosed herein are a video decoding method and apparatus and a video encoding method and apparatus. A virtual frame is generated by a video generation network including a generation encoder and a generation decoder. The virtual frame is used as a reference frame in inter prediction for a target. Further, a video generation network for inter prediction may be selected from among multiple video generation networks, and inter prediction that uses the selected video generation network may be performed.

Method and apparatus for video encoding and video decoding based on neural network

Disclosed herein are a video decoding method and apparatus and a video encoding method and apparatus. In quantization and dequantization, multiple quantization methods and multiple dequantization methods may be used. The multiple quantization methods include a variable-rate step quantization method and a fixed-rate step quantization method. The variable-rate step quantization method may be a quantization method in which an increment in a quantization step depending on an increase in a value of a quantization parameter by 1 is not fixed. The fixed-rate step quantization method may be a quantization method in which the increment in the quantization step depending on the increase of the value of the quantization parameter by 1 is fixed.

Method and apparatus for quantization

An apparatus and method perform rate-distortion optimization based on cost. The encoding apparatus selects an encoding mode to be used to encode a target block from among multiple modes and performs computation for rate-distortion optimization in the encoding mode. The encoding apparatus calculates a cost of at least one of the multiple modes in relation to the encoding of the target block, and selects the encoding mode from among the multiple modes, based on the cost.

Apparatus and method for performing rate-distortion optimization based on Hadamard-quantization cost

A fast block mode determining method for motion estimation, and an apparatus thereof. A cost of motion estimation for an input image frame is predicted by Kalman filtering, and one block mode is selected from a plurality of block modes. A cost for the motion estimation of the input image frame is calculated. The predicted cost and the calculated cost are compared with each other, and the block mode for performing the motion estimation is determined. In an H.264 moving picture encoding device, the operation load is reduced and time wasted for calculation is shortened, because it is not necessary to perform the motion estimation for all the block modes.

Growing community of inventors

Daejeon, South Korea

Jin-Wuk Seok