Temporal Consistency Learning of inter-frames for Video Super-Resolution

TL;DR

This paper introduces TCNet, a novel end-to-end network for video super-resolution that emphasizes temporal consistency through self-alignment, correlation, and attention mechanisms, leading to superior results.

Contribution

The paper proposes a comprehensive temporal consistency learning framework with a spatio-temporal stability module, self-attention, and hybrid recurrent architecture for improved VSR performance.

Findings

TCNet outperforms state-of-the-art methods on benchmark datasets.

The proposed modules enhance temporal stability and structural preservation.

Experiments validate the effectiveness of the multi-stage fusion approach.

Abstract

Video super-resolution (VSR) is a task that aims to reconstruct high-resolution (HR) frames from the low-resolution (LR) reference frame and multiple neighboring frames. The vital operation is to utilize the relative misaligned frames for the current frame reconstruction and preserve the consistency of the results. Existing methods generally explore information propagation and frame alignment to improve the performance of VSR. However, few studies focus on the temporal consistency of inter-frames. In this paper, we propose a Temporal Consistency learning Network (TCNet) for VSR in an end-to-end manner, to enhance the consistency of the reconstructed videos. A spatio-temporal stability module is designed to learn the self-alignment from inter-frames. Especially, the correlative matching is employed to exploit the spatial dependency from each frame to maintain structural stability. Moreover, a self-attention mechanism is utilized to learn the temporal correspondence to implement an adaptive warping operation for temporal consistency among multi-frames. Besides, a hybrid recurrent architecture is designed to leverage short-term and long-term information. We further present a progressive fusion module to perform a multistage fusion of spatio-temporal features. And the final reconstructed frames are refined by these fused features. Objective and subjective results of various experiments demonstrate that TCNet has superior performance on different benchmark datasets, compared to several state-of-the-art methods.