Reference-based Video Super-Resolution Using Multi-Camera Video Triplets

Authors:

Abstract
We propose the first reference-based video super-resolution (RefVSR) approach that utilizes reference videos for high-fidelity results. We focus on RefVSR in a triple-camera setting, where we aim at super-resolving a low-resolution ultra-wide video utilizing wide-angle and tele-photo videos. We introduce the first RefVSR network that re-currently aligns and propagates temporal reference features fused with features extracted from low-resolution frames. To facilitate the fusion and propagation of temporal reference features, we propose a propagative temporal fusion module. For learning and evaluation of our network, we present the first RefVSR dataset consisting of triplets of ultra-wide, wide-angle, and telephoto videos concurrently taken from triple cameras of a smartphone. We also propose a two-stage training strategy fully utilizing video triplets in the proposed dataset for real-world 4 × video super-resolution. We extensively evaluate our method, and the result shows the state-of-the-art performance in 4 × super-resolution.
Funding Information
  • IITP (2015-0-00174)
  • NRF (2018R1A5A1060031,2020R1C1C1014863)