Dynamically Expanded CNN Array for Video Coding

Video coding is a critical step in all popular methods of streaming video. Marked progress has been made in video quality, compression, and computational efficiency. Recently, there has been an interest in finding ways to apply techniques from the fast-progressing field of Machine Learning to further improve video coding. We present a method that uses convolutional neural networks to help refine the output of various standard coding methods. The novelty of our approach is to train multiple different groups of network parameters, with each set corresponding to a specific, short segment of video and arranging the groups in a hierarchy that reflects their locality within the video. Low-level groups are updated often and specialize on local features while high-level groups find non-local features that can be used for longer segments of video. The parameter groups expand dynamically to match a video of any length. We show that our method can improve the quality of standard video codecs without increasing in compressed video size.