• Journal of Broadcast Engineering
• /
• v.27 no.7
• /
• pp.1021-1033
• /
• 2022

After the Versatile Video Coding (VVC)/H.266 standard was completed, the Joint Video Exploration Team (JVET) began to investigate new technologies that could significantly increase coding gain for the next generation video coding standard. One direction is to investigate signal processing based tools, while the other is to investigate Neural Network based technology. Neural Network based Video Coding (NNVC) has not been studied previously, and this is the first trial of such an approach in the standard group. After two years of research, JVET produced the first common software called Neural Compression Software (NCS) with two NN-based in-loop filtering tools at the 27th meeting and began to maintain NN-based technologies for the common experiment. The coding performances of the two filters in NCS-1.0 are shown to be 8.71% and 9.44% on average in a random access scenario, respectively. All the material related to NCS can be found in the repository of the JVET. In this paper, we provide a brief overview and review of the NNVC activity studied in JVET in order to provide trend and insight for the new direction of video coding standard.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2022.11a
• /
• pp.8-9
• /
• 2022

최근 VVC(Versatile Video Coding) 표준 완료 이후 JVET(Joint Video Experts Team)에서는 NNVC(Neural Network-based Video Coding) EE(Exploration Experiment)를 통하여 화면내 예측을 포함한 신경망 기반의 부호화 기술들을 탐색하고 검증하고 있다. 본 논문에서는 VVC 에 채택되어 있는 다중 변환 선택(MTS: Multiple Transform Selection)에 따라서 적절한 예측 블록을 선택할 수 있는 TDIP(Transform-Dependent Intra Prediction) 모델을 제안한다. 실험결과 제안기법은 VVC 의 AI(All Intra) 부호화 환경에서 VTM(VVC Test Model) 대비 Y, U, V 에 각각 0.87%, 0.87%, 0.99%의 BD-rate 절감의 비디오 부호화 성능 향상을 보였다.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2021.06a
• /
• pp.311-312
• /
• 2021

최근 VVC(Versatile Video Coding) 표준 완료 이후 JVET(Joint Video Experts Team)은 NNVC(Neural Network-based Video Coding) AhG(Ad-hoc Group)을 구성하고 인공지능을 이용한 비디오 압축 기술들을 탐색하고 있다. 본 논문에서는 VVC 복원 영상의 DCT 계수를 기반으로 복원 영상을 분류하고, 분류된 각 클래스에 따라 적응적으로 CNN(Convolutional Neural Network) 기반의 화질 개선을 수행하는 VVC 후처리 기법을 제안한다. 실험결과, 제안기법은 AI(All Intra) 부호화 모드에서 1.23% BD-rate 이득을 보였다.