跳到主要导航 跳到搜索 跳到主要内容

Beyond Keypoint Coding: Temporal Evolution Inference with Compact Feature Representation for Talking Face Video Compression

  • Bolin Chen*
  • , Zhao Wang
  • , Binzhe Li*
  • , Rongqun Lin*
  • , Shiqi Wang*
  • , Yan Ye
  • *此作品的通讯作者
  • City University of Hong Kong
  • Alibaba Group Holding Ltd.

科研成果: 书/报告/会议事项章节会议稿件同行评审

摘要

We propose a talking face video compression framework by implicitly transforming the temporal evolution into compact feature representation. More specifically, the temporal evolution of faces, which is complex, non-linear and difficult to extrapolate, is modelled in an end-to-end inference framework based upon very compact features. This enables the high-quality rendering of the face videos, which benefits from the learning of dense motion map with compact feature representation. Therefore, the proposed framework can accommodate ultra-low bandwidth video communication and maintain the quality of the reconstructed videos. Experimental results demonstrate that compared with the state-of-the-art video coding standard Versatile Video Coding (VVC) as well as the latest generative compression scheme Face Video-to-Video Synthesis (Facevid2vid), the proposed scheme is superior in terms of both objective and subjective quality assessment methods.

源语言英语
主期刊名Proceedings - DCC 2022
主期刊副标题2022 Data Compression Conference
编辑Ali Bilgin, Michael W. Marcellin, Joan Serra-Sagrista, James A. Storer
出版商Institute of Electrical and Electronics Engineers Inc.
13-22
页数10
ISBN(电子版)9781665478939
DOI
出版状态已出版 - 2022
已对外发布
活动2022 Data Compression Conference, DCC 2022 - Snowbird, 美国
期限: 22 3月 202225 3月 2022

出版系列

姓名Data Compression Conference Proceedings
2022-March
ISSN(印刷版)1068-0314

会议

会议2022 Data Compression Conference, DCC 2022
国家/地区美国
Snowbird
时期22/03/2225/03/22

指纹

探究 'Beyond Keypoint Coding: Temporal Evolution Inference with Compact Feature Representation for Talking Face Video Compression' 的科研主题。它们共同构成独一无二的指纹。

引用此