ETRI-Knowledge Sharing Plaform

ENGLISH

성과물

논문 검색
구분 SCI
연도 ~ 키워드

상세정보

학술대회 Convolution Neural Network based Video Coding Technique using Reference Video Synthesis
Cited 13 time in scopus Download 0 time Share share facebook twitter linkedin kakaostory
저자
이정경, 김나영, 조승현, 강제원
발행일
201811
출처
Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA-ASC) 2018, pp.505-508
DOI
https://dx.doi.org/10.23919/APSIPA.2018.8659611
협약과제
18HR2300, [통합과제] 초실감 테라미디어를 위한 AV부호화 및 LF미디어 원천기술 개발, 최진수
초록
In this paper, we propose a novel video coding technique that uses a virtual reference (VR) video frame, synthesized by a convolution neural network (CNN) for an inter-coding. Specifically, an encoder generates a VR frame from a video interpolation CNN (VI-CNN) using two reconstructed pictures, i.e., one from the forward reference frames and the other from the backward reference frames. The VR frame is included into the reference picture lists to exploit further temporal correlation in motion estimation and compensation. It is demonstrated by the experimental results that the proposed technique shows about 1.4% BD-rate reductions over the HEVC reference test model (HM 16.9) as an anchor in a Random Access (RA) coding scenario.
KSP 제안 키워드
Convolution neural network(CNN), Motion estimation(ME), Random Access, Reference frame, Temporal Correlation, Video coding, Video interpolation, estimation and compensation, test model, video frames, video synthesis