Cardiff University | Prifysgol Caerdydd ORCA
Online Research @ Cardiff 
WelshClear Cookie - decide language by browser settings

Deformable non-local network for video super-resolution

Wang, Hua, Su, Dewei, Liu, Chuangchuang, Jin, Longcun, Sun, Xianfang ORCID: and Peng, Xinyi 2019. Deformable non-local network for video super-resolution. IEEE Access 7 , pp. 177734-177744. 10.1109/ACCESS.2019.2958030

[thumbnail of 08926405.pdf]
PDF - Published Version
Available under License Creative Commons Attribution.

Download (4MB) | Preview


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 nonlocal 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 nonlocal 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 highquality 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.

Item Type: Article
Date Type: Publication
Status: Published
Schools: Computer Science & Informatics
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
ISSN: 2169-3536
Related URLs:
Date of First Compliant Deposit: 16 December 2019
Date of Acceptance: 2 December 2019
Last Modified: 04 May 2023 19:15

Citation Data

Cited 27 times in Scopus. View in Scopus. Powered By Scopus® Data

Actions (repository staff only)

Edit Item Edit Item


Downloads per month over past year

View more statistics