Deformable Non-local Network for Video Super-Resolution

TL;DR

This paper introduces a deformable non-local network for video super-resolution that avoids optical flow, using adaptive feature alignment and global correlation to improve high-resolution video reconstruction.

Contribution

The proposed DNLN method is a novel non-optical-flow-based approach that enhances feature alignment and detail preservation in VSR.

Findings

Achieves state-of-the-art performance on benchmark datasets.

Effectively captures global correlations for better detail restoration.

Improves adaptive alignment without optical flow errors.

Abstract

The video super-resolution (VSR) task aims to restore a high-resolution (HR) video frame by using its corresponding low-resolution (LR) frame and multiple neighboring frames. At present, many deep learning-based VSR methods rely on optical flow to perform frame alignment. The final recovery results will be greatly affected by the accuracy of optical flow. However, optical flow estimation cannot be completely accurate, and there are always some errors. In this paper, we propose a novel deformable non-local network (DNLN) which is a non-optical-flow-based method. Specifically, we apply the deformable convolution and improve its ability of adaptive alignment at the feature level. Furthermore, we utilize a non-local structure to capture the global correlation between the reference frame and the aligned neighboring frames, and simultaneously enhance desired fine details in the aligned frames. To reconstruct the final high-quality HR video frames, we use residual in residual dense blocks to take full advantage of the hierarchical features. Experimental results on benchmark datasets demonstrate that the proposed DNLN can achieve state-of-the-art performance on VSR task.