跳到主要导航 跳到搜索 跳到主要内容

Improving Optical Flow Inference for Video Colorization

  • Rulin Huang
  • , Shaohui Li
  • , Wenrui Dai*
  • , Chenglin Li
  • , Junni Zou
  • , Hongkai Xiong
  • *此作品的通讯作者
  • Shanghai Jiao Tong University

科研成果: 书/报告/会议事项章节 › 会议稿件 › 同行评审

摘要

Recent video colorization methods optimize correspondence estimation and information propagation in an end-to-end manner. However, they usually suffer from loss of fidelity due to the inaccurate inference of correspondence measurement. In this paper, we propose a post-training optimization (PTO) strategy to refine correspondence measurement in the end-to-end optimized framework. The proposed PTO strategy introduces a pseudo loss function to well approximate the target loss and guide the direction of updates. We further develop a video colorization method that incorporates PTO and optical flow to guarantee high-fidelity colorized frames in theory. Experimental results demonstrate that the proposed method achieves state-of-the-art PSNR performance in video colorization on the DAVIS dataset and common test sequences for video coding. Furthermore, the proposed method can be employed into video compression and achieves competitive rate-distortion performance with the recent High Efficiency Video Coding (HEVC) standard.

源语言英语
主期刊名IEEE International Symposium on Circuits and Systems, ISCAS 2022
出版商Institute of Electrical and Electronics Engineers Inc.
页3185-3189
页数5
ISBN(电子版)9781665484855
DOI
出版状态已出版 - 2022
已对外发布是
活动2022 IEEE International Symposium on Circuits and Systems, ISCAS 2022 - Austin, 美国
期限: 27 5月 2022 → 1 6月 2022

丛书

姓名Proceedings - IEEE International Symposium on Circuits and Systems
卷2022-May
ISSN(印刷版)0271-4310

会议

会议2022 IEEE International Symposium on Circuits and Systems, ISCAS 2022
国家/地区美国
市Austin
时期27/05/22 → 1/06/22

学术指纹

探究 'Improving Optical Flow Inference for Video Colorization' 的科研主题。它们共同构成独一无二的学术指纹。

引用此