Prediction-assistant Frame Super-Resolution for Video Streaming

Abstract

Video frame transmission delay is critical in real-time applications such as online video gaming, live show, etc. The receiving deadline of a new frame must catch up with the frame rendering time. Otherwise, the system will buffer a while, and the user will encounter a frozen screen, resulting in unsatisfactory user experiences. An effective approach is to transmit frames in lower-quality under poor bandwidth conditions, such as using scalable video coding. In this paper, we propose to enhance video quality using lossy frames in two situations. First, when current frames are too late to receive before rendering deadline (i.e., lost), we propose to use previously received high-resolution images to predict the future frames. Second, when the quality of the currently received frames is low (i.e., lossy), we propose to use previously received high-resolution frames to enhance the low-quality current ones. For the first case, we propose a small yet effective video frame prediction network. For the second case, we improve the video prediction network to a video enhancement network to associate current frames as well as previous frames to restore highquality images. Extensive experimental results demonstrate that our method performs favorably against state-of-the-art algorithms in the lossy video streaming environment. We will publish the source code and the pre-trained models upon acceptance.

H2-Stereo: High-Speed, High-Resolution Stereoscopic Video System

“…Super-resolution methods, such as single-image superresolution [14], [16], [17], video super-resolution [37], [1], [18], [38] and multi-view image super-resolution [19], [20], aim to restore the high-resolution images from low-resolution inputs. All of these approaches can not restore sharp spatial details for high-resolution reconstruction due to the severe loss of high-frequency spatial information.…”