A Novel Dual Dense Connection Network for Video Super-resolution

TL;DR

This paper introduces a dual dense connection network for video super-resolution that effectively utilizes temporal information and a new loss function, achieving superior results on standard datasets.

Contribution

The paper proposes a novel dual dense connection network with a unique frame grouping strategy and a new loss function for improved video super-resolution.

Findings

Outperforms existing models on Vid4 and SPMCS-11 datasets

Effectively utilizes temporal information without disorder

Enhances convergence with a new loss function

Abstract

Video super-resolution (VSR) refers to the reconstruction of high-resolution (HR) video from the corresponding low-resolution (LR) video. Recently, VSR has received increasing attention. In this paper, we propose a novel dual dense connection network that can generate high-quality super-resolution (SR) results. The input frames are creatively divided into reference frame, pre-temporal group and post-temporal group, representing information in different time periods. This grouping method provides accurate information of different time periods without causing time information disorder. Meanwhile, we produce a new loss function, which is beneficial to enhance the convergence ability of the model. Experiments show that our model is superior to other advanced models in Vid4 datasets and SPMCS-11 datasets.