论文标题
使用深图像动画的超低比特量视频会议
Ultra-low bitrate video conferencing using deep image animation
论文作者
论文摘要
在这项工作中，我们提出了一种新颖的深度学习方法，用于用于视频会议应用程序的超低比特率视频压缩。为了解决当前视频压缩范式的缺点，当可用的带宽非常有限时，我们采用了一种基于模型的方法，该方法采用深层神经网络将运动信息编码为关键点位移并在解码器端重建视频信号。总体系统以端到端的方式进行了训练，以最大程度地减少编码器输出的重建错误。客观和主观的质量评估实验表明，与HEVC相比，所提出的方法为相同的80％以上的视觉质量提供了平均比特率降低。
In this work we propose a novel deep learning approach for ultra-low bitrate video compression for video conferencing applications. To address the shortcomings of current video compression paradigms when the available bandwidth is extremely limited, we adopt a model-based approach that employs deep neural networks to encode motion information as keypoint displacement and reconstruct the video signal at the decoder side. The overall system is trained in an end-to-end fashion minimizing a reconstruction error on the encoder output. Objective and subjective quality evaluation experiments demonstrate that the proposed approach provides an average bitrate reduction for the same visual quality of more than 80% compared to HEVC.
