A new way of video compression via forward-referencing using deep learning. (arXiv:2208.06678v1 [cs.CV])

To exploit high temporal correlations in video frames of the same scene, the
current frame is predicted from the already-encoded reference frames using
block-based motion estimation and compensation techniques. While this approach
can efficiently exploit the translation motion of the moving objects, it is
susceptible to other types of affine motion and object occlusion/deocclusion.
Recently, deep learning has been used to model the high-level structure of
human pose in specific actions from short videos and then generate virtual
frames in …

arxiv compression cv deep learning learning video video compression