Diffusion probabilistic models have recently achieved remarkable success...
In video compression, coding efficiency is improved by reusing pixels fr...
Realizing the potential of neural video codecs on mobile devices is a bi...
Humans do not perceive all parts of a scene with the same resolution, bu...
When training end-to-end learned models for lossy compression, one has t...
Recent advances in deep generative modeling have enabled efficient model...
In this work, we propose a new recurrent autoencoder architecture, terme...