Hybrid model-and-object-based real-time conversational video coding
作者：
Highlights：
• A low bit-rate conversational video coding method is proposed.
• The face region is tracked with a face model and coded with model-based coding.
• The head-shoulder region is segmented and coded with mesh-based coding.
• The two regions are integrated; bit-allocation is performed by joint optimization.
• Rate-distortion improvements of more than 5 dB over existing methods were observed.
摘要
Highlights•A low bit-rate conversational video coding method is proposed.•The face region is tracked with a face model and coded with model-based coding.•The head-shoulder region is segmented and coded with mesh-based coding.•The two regions are integrated; bit-allocation is performed by joint optimization.•Rate-distortion improvements of more than 5 dB over existing methods were observed.
论文关键词：Model-based video coding,Object-based video coding,Face modeling
论文评审过程：Received 26 May 2014, Revised 19 January 2015, Accepted 24 March 2015, Available online 1 April 2015.
论文官网地址：https://doi.org/10.1016/j.image.2015.03.009
