상세정보
학술대회
Video Generation and Synthesis Network for Long-term Video Interpolation
- 저자
- 김나영, 이정경, 유채화, 조승현, 강제원
- 발행일
- 201811
- 출처
- Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA-ASC) 2018, pp.705-709
- 협약과제
- 18HR2300, [통합과제] 초실감 테라미디어를 위한 AV부호화 및 LF미디어 원천기술 개발, 최진수
- 초록
- In this paper, we propose a bidirectional synthesis video interpolation technique based on deep learning, using a forward and a backward video generation network and a synthesis network. The forward generation network first extrapolates a video sequence, given the past video frames, and then the backward generation network generates the same video sequence, given the future video frames. Next, a synthesis network fuses the results of the two generation networks to create an intermediate video sequence. To jointly train the video generation and synthesis networks, we define a cost function to approximate the visual quality and the motion of the interpolated video as close as possible to those of the original video. Experimental results show that the proposed technique outperforms the state-of-the art long-term video interpolation model based on deep learning.
- KSP 제안 키워드
- Cost Function, Interpolation model, Video generation, Video interpolation, Visual Quality, deep learning(DL), interpolation technique, model-based, state-of-The-Art, video frames, video sequences