Deep Video Super-Resolution Using HR Optical Flow Estimation

Video super-resolution (SR) aims at generating a sequence of high-resolution (HR) frames with plausible and temporally consistent details from their low-resolution (LR) counterparts. The key challenge for video SR lies in the effective exploitation of temporal dependency between consecutive frames. Existing deep learning based methods commonly estimate optical flows between LR frames to provide temporal dependency. However, the resolution conflict between LR optical flows and HR outputs hinders the recovery of fine details. In this paper, we propose an end-to-end video SR network to super-resolve both optical flows and images. Optical flow SR from LR frames provides accurate temporal dependency and ultimately improves video SR performance. Specifically, we first propose an optical flow reconstruction network (OFRnet) to infer HR optical flows in a coarse-to-fine manner. Then, motion compensation is performed using HR optical flows to encode temporal dependency. Finally, compensated LR inputs are fed to a super-resolution network (SRnet) to generate SR results. Extensive experiments have been conducted to demonstrate the effectiveness of HR optical flows for SR performance improvement. Comparative results on the Vid4 and DAVIS-10 datasets show that our network achieves the state-of-the-art performance.

I. Introduction

Super-resolution (SR) aims at generating high-resolution (HR) images from their low-resolution (LR) counterparts. As a typical low-level computer vision problem, SR has been investigated for decades [1]–[3]. Recently, converting LR videos into HR ones, namely video SR, is under great demand due to the prevalence of high-definition displays. Compared to a single image, adjacent frames in a video clip provide additional information for SR. Therefore, exploiting temporal dependency between consecutive frames plays an important role in video SR.