阅读说明：本技术 使用深度生成性模型的视频压缩 (Video compression using depth generative models ) 是由 A·哈比比安 T·S·科恩 于 2020-03-19 设计创作，主要内容包括：本公开的某些方面涉及用于使用深度生成性模型来压缩视频内容的方法和装置。一种示例方法一般包括接收用于压缩的视频内容。一般通过自编码器将所接收的视频内容编码到隐代码空间中,该自编码器可由第一人工神经网络来实现。一般通过经训练的概率模型(经训练的概率模型可由第二人工神经网络实现)来生成经编码视频内容的经压缩版本,并且输出以供传输。(Certain aspects of the present disclosure relate to methods and apparatus for compressing video content using a depth generative model. An example method generally includes receiving video content for compression. The received video content is typically encoded into the steganographic code space by an auto-encoder, which may be implemented by a first artificial neural network. A compressed version of the encoded video content is typically generated by a trained probabilistic model (which may be implemented by a second artificial neural network) and output for transmission.)