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·J·范罗森达尔 T·S·科恩 于 2020-03-23 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：接收供压缩的视频内容。所接收的视频内容一般通过可由第一人工神经网络实现的编码器被编码到隐性码空间中。经编码视频内容的经压缩版本一般通过可由第二人工神经网络实现的经训练概率性模型来生成并输出以供传输。(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: video content is received for compression. The received video content is typically encoded into an implicit code space by an encoder that may be implemented by a first artificial neural network. A compressed version of the encoded video content is typically generated and output for transmission through a trained probabilistic model that may be implemented by a second artificial neural network.)