Research Area:  Machine Learning

Abstract:

Video super-resolution is currently one of the most active research topics in computer vision as it plays an important role in many visual applications. Generally, video super-resolution contains a significant component, i.e., motion compensation, which is used to estimate the displacement between successive video frames for temporal alignment. Optical flow, which can supply dense and sub-pixel motion between consecutive frames, is among the most common ways for this task. To obtain a good understanding of the effect that optical flow acts in video super-resolution, in this work, we conduct a comprehensive review on this subject for the first time. This investigation covers the following major topics: the function of super-resolution (i.e., why we require super-resolution); the concept of video super-resolution (i.e., what is video super-resolution); the description of evaluation metrics (i.e., how (video) super-resolution performs); the introduction of optical flow based video super-resolution; the investigation of using optical flow to capture temporal dependency for video super-resolution. Prominently, we give an in-depth study of the deep learning based video super-resolution method, where some representative algorithms are analyzed and compared. Additionally, we highlight some promising research directions and open issues that should be further addressed.

Keywords:  
Video super-resolution Optical flow Optical Flow-based video super-resolution Temporal dependency

Author(s) Name:  Zhigang Tu, Hongyan Li, Wei Xie, Yuanzhong Liu, Shifu Zhang, Baoxin Li & Junsong Yuan

Publisher name:  Springer

DOI:  10.1007/s10462-022-10159-8

Volume Information:  volume 55, pages: 6505–6546

Paper Link:   https://link.springer.com/article/10.1007/s10462-022-10159-8