SuperTran: Reference Based Video Transformer for Enhancing Low Bitrate Streams in Real Time

TL;DR

SuperTran is a real-time deep generative model that enhances low bitrate videos by combining reference images with the video stream to improve perceptual quality through super-resolution and artifact removal.

Contribution

It introduces a novel reference-based video transformer that significantly improves low bitrate video quality in real-time, surpassing existing methods that only use low-resolution inputs.

Findings

Achieves real-time processing at 30 fps on the cloud.

Produces perceptually enhanced videos with better detail than previous methods.

Effectively utilizes reference images to improve visual quality.

Abstract

This work focuses on low bitrate video streaming scenarios (e.g. 50 - 200Kbps) where the video quality is severely compromised. We present a family of novel deep generative models for enhancing perceptual video quality of such streams by performing super-resolution while also removing compression artifacts. Our model, which we call SuperTran, consumes as input a single high-quality, high-resolution reference images in addition to the low-quality, low-resolution video stream. The model thus learns how to borrow or copy visual elements like textures from the reference image and fill in the remaining details from the low resolution stream in order to produce perceptually enhanced output video. The reference frame can be sent once at the start of the video session or be retrieved from a gallery. Importantly, the resulting output has substantially better detail than what has been otherwise possible with methods that only use a low resolution input such as the SuperVEGAN method. SuperTran works in real-time (up to 30 frames/sec) on the cloud alongside standard pipelines.