Electronics and Telecommunications Research Institute

Lg Electronics Inc.

Ewha University-Industry Collaboration Foundation

Je-Won Kang

Seung-Hyun Cho

Hui-Yong Kim

Jong-Ho Kim

Se-Yoon Jeong

Jin-Soo Choi

Woong Lim

Joo-Young Lee

Youn-Hee Kim

Jin-Wuk Seok

Dae-Yeol Lee

Na-Young Kim

Jaehyun Lim

Sunmi Yoo Yoo

Jaeho Lee

Hyunsuk Ko

Soo Kyung Ryu

Min-Joo Kang

Jung-Kyung Lee

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

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 is a method for encoding/decoding a still image or moving image based on an intra-prediction mode and an apparatus supporting the same. Particularly, a method for processing an image based on an intra prediction mode may include determining an intra prediction mode set used for an intra prediction in a current prediction processing unit among multiple intra prediction mode sets having different resolutions with each other, wherein the resolution represents a degree of distribution of the intra prediction mode in the intra prediction mode set; deriving an intra prediction mode applied to the current prediction processing unit in the determined intra prediction mode set using index information received from an encoder; and generating a prediction sample of the current prediction processing unit based on the derived intra prediction mode, and each of the intra prediction mode sets includes one or more intra prediction modes.

Intra prediction mode-based image processing method, and apparatus therefor

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

Growing community of inventors

Seoul, South Korea

Je-Won Kang