loading page

Online Video Super-Resolution using Unidirectional Recurrent Model
  • +2
  • Arbind Agrahari Baniya ,
  • Glory Lee ,
  • Peter Eklund ,
  • Sunil Aryal ,
  • Antonio Robles-Kelly
Arbind Agrahari Baniya
Deakin University, Deakin University

Corresponding Author:[email protected]

Author Profile
Glory Lee
Author Profile
Peter Eklund
Author Profile
Sunil Aryal
Author Profile
Antonio Robles-Kelly
Author Profile

Abstract

This is an original research article entitled “Online Video Super-Resolution using Unidirectional Recurrent Model”. Considering the critical constraints around video frames and resource availability in an online setting, this paper presents a new unidirectional video super-resolution (VSR) model with a recurrent architecture specifically designed for online applications. Many recent works in the video super-resolution domain focus on improving the super-resolution quality at the cost of computationally intense and input-heavy bidirectional modelling. To alleviate these drawbacks, we propose the Replenished Recurrency with Dual-Duct (R2D2) model which adopts unidirectional architecture to fully utilise local features and global memory available at each timestamp. The two variants – R2D2 and R2D2-lite presented in the paper generate state-of-the-art super-resolution quality at significantly optimised efficiency. This is believed an important step forward in real-world applications-inspired research in the video super-resolution domain.
Aug 2023Published in Neurocomputing volume 546 on pages 126355. 10.1016/j.neucom.2023.126355