Online Video Super-Resolution with Convolutional Kernel Bypass Graft

TL;DR

This paper introduces a low-latency, real-time video super-resolution method called CKBG that uses kernel knowledge transfer to enhance a lightweight model, achieving high frame rates suitable for online applications.

Contribution

The paper proposes a novel kernel knowledge transfer method, CKBG, for real-time video super-resolution that combines low latency, low complexity, and competitive performance.

Findings

Processes up to 110 FPS in online video sequences.

Uses a lightweight network without future frame inputs.

Achieves competitive super-resolution quality.

Abstract

Deep learning-based models have achieved remarkable performance in video super-resolution (VSR) in recent years, but most of these models are less applicable to online video applications. These methods solely consider the distortion quality and ignore crucial requirements for online applications, e.g., low latency and low model complexity. In this paper, we focus on online video transmission, in which VSR algorithms are required to generate high-resolution video sequences frame by frame in real time. To address such challenges, we propose an extremely low-latency VSR algorithm based on a novel kernel knowledge transfer method, named convolutional kernel bypass graft (CKBG). First, we design a lightweight network structure that does not require future frames as inputs and saves extra time costs for caching these frames. Then, our proposed CKBG method enhances this lightweight base model by bypassing the original network with ``kernel grafts'', which are extra convolutional kernels containing the prior knowledge of external pretrained image SR models. In the testing phase, we further accelerate the grafted multi-branch network by converting it into a simple single-path structure. Experiment results show that our proposed method can process online video sequences up to 110 FPS, with very low model complexity and competitive SR performance.