Sign up for FREE access to the latest industry trends, videos, thought leadership articles, executive interviews, behind the scenes exclusives and more!

Several research groups worldwide are currently investigating how deep learning may advance the state-of-the-art in image and video coding. An open question is how to make deep neural networks work in conjunction with existing (and upcoming) video codecs, such as MPEG AVC/H.264, Such compatibility is a crucial aspect, as the video content industry and hardware manufacturers are expected to remain committed to supporting these standards for the foreseeable future. We propose deep neural networks as precoding components for current and future codec ecosystems. In our current deployments for DASH/HLS adaptive streaming, this comprises downscaling neural networks.