In many digital systems, the transmission bandwidth, as well as storage capacity, are usually very limited. This introduces challenges for both video transmission and video storage. One of the efficient solutions to this problem is to compress the down-sampled frames and then process up-sampling/super-resolution after decoding. To seek lower bit rates and further obtain high-quality up-sampled videos, this paper proposes a temporal down-sampling based
video coding system and a frame-recurrent enhancement based video upsampling strategy.
In this new approach, instead of downsampling all video frames, only the intermediate frames are downsampled and two frames remain with high quality. Then, these two highquality frames are used to iteratively enhance the quality of the low-bitrate low-quality frames through a deep-learned enhancement network. Compared to the latest video coding standard Versatile Video Coding (VVC), our work can obtain a BD-rate reduction from 39.261% ~ 85.455 % in All-Intra and Low -Delay-P configurations on the downsampled frames.