Electronics and Telecommunications Research Institute

Korea University Research and Business Foundation

Youn-Hee Kim

Jin-Soo Choi

Se-Yoon Jeong

Joo-Young Lee

Jong-Ho Kim

Hui-Yong Kim

Jin-Wuk Seok

Seung-Hyun Cho

Dong-Hyun Kim

Woong Lim

Tae-Jin Lee

Hyoung-Jin Kwon

Dae-Yeol Lee

Ji-Hoon Do

Seoung-Jun Oh

Dong-Gyu Sim

Hyunsuk Ko

Je-Won Kang

Min-Hun Lee

Jee-Hoon Kim

Kwang-Hwan Kim

Han-Sol Choi

Na-Young Kim

Yun-gu Lee

Seung-Kwon Beack

Seung-won Jung

Dong-Wook Kim

Myung-Seok Ki

Jung-Kyung Lee

Yun-Gu Lee

Disclosed herein are a method, an apparatus, and a storage medium for image encoding/decoding using filtering. The image encoding method and the image decoding method perform classification on a classification unit of a target image, and perform filtering that uses a filter on the classification unit. A classification index of the classification unit is determined, and the classification index indicates a filter to be used for filtering on the classification unit, among multiple filters. The classification index is determined by various coding parameters, such as an encoding mode of the target block and an encoding mode of a neighboring block adjacent to the target block.

Method, apparatus and storage medium for image encoding/decoding using filtering

An encoding apparatus extracts features of an image by applying multiple padding operations and multiple downscaling operations to an image represented by data and transmits feature information indicating the features to a decoding apparatus. The multiple padding operations and the multiple downscaling operations are applied to the image in an order in which one padding operation is applied and thereafter one downscaling operation corresponding to the padding operation is applied. A decoding method receives feature information from an encoding apparatus, and generates a reconstructed image by applying multiple upscaling operations and multiple trimming operations to an image represented by the feature information. The multiple upscaling operations and the multiple trimming operations are applied to the image in an order in which one upscaling operation is applied and thereafter one trimming operation corresponding to the upscaling operation is applied.

Method, apparatus, and storage medium using padding/trimming in compression neural network

There are provided a method, apparatus, system, and computer-readable recording medium for image compression. An encoding apparatus performs domain transformation and quantization on feature map information and image information. The encoding apparatus rearranges the result of domain transformation and quantization so as to have a form advantageous to the encoding procedure and encodes the result of rearrangement, thereby generating a bitstream. A decoding apparatus receives the bitstream, decodes the received bitstream, and performs inverse transformation, dequantization, and inverse rearrangement using information transmitted through the bitstream. The result of inverse transformation, dequantization, and inverse rearrangement is used for the machine-learning task of a neural network.

Method, apparatus, system and computer-readable recording medium for feature information

Disclosed herein are a method, an apparatus, and a storage medium for image encoding/decoding. An intra-prediction mode for the target block is derived, and intra-prediction for the target block that uses the derived intra-prediction mode is performed. The intra-prediction mode for the target block is derived using an artificial neural network, and an MPM list for the target block is derived using information about the target block, pieces of information about blocks adjacent to the target block, and the artificial neural network. The artificial neural network outputs one or more available intra-prediction modes. Further, the artificial neural network outputs match probabilities for one or more candidate intra-prediction modes, and each of the match probabilities for the candidate intra-prediction modes indicates a probability that the corresponding candidate intra-prediction mode matches the intra-prediction mode for the target block.

Apparatus, method and storage medium for image encoding/decoding to perform intra prediction using artificial neutral network

There are provided an apparatus, method, system, and recording medium for performing selective encoding/decoding on feature information. An encoding apparatus generates residual feature information. The encoding apparatus transmits the residual feature information to a decoding apparatus through a residual feature map bitstream. The residual feature information is the difference between feature information extracted from an original image and feature information extracted from a reconstructed image. Feature information of the reconstructed image is generated using the reconstructed image. Reconstructed feature information is generated using the feature information of the reconstructed image and reconstructed residual feature information.

Disclosed herein are a method, an apparatus and a storage medium for image encoding/decoding using a binary mask. An encoding method includes generating a latent vector using an input image, generating a selected latent vector component set using a binary mask, and generating a main bitstream by performing entropy encoding on the selected latent vector component set. A decoding method includes generating a selected latent vector component set including one or more selected latent vector components by performing entropy decoding on a main bitstream and generating the latent vector in which the one or more selected latent vector components are relocated by relocating the selected latent vector component set in the latent vector.

Method, apparatus and storage medium for image encoding/decoding using binary mask

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

Disclosed herein are a method, apparatus, system, and computer-readable recording medium for image compression. An encoding apparatus performs preprocessing of feature map information, frame packing, frame classification, and encoding. A decoding apparatus performs decoding, frame depacking, and postprocessing in order to reconstruct feature map information. By encoding the feature map information, inter-prediction and intra-block prediction for a frame are performed. The encoding apparatus provides the decoding apparatus with a feature map information bitstream for reconstructing the feature map information along with an image information bitstream.

Method, apparatus, system and computer-readable recording medium for feature map information

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.

Growing community of inventors

Daejeon, South Korea

Youn-Hee Kim