Reference-based Video Super-Resolution Using Multi-Camera Video Triplets
Authors:
- 1 June 2022
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 17803-17812
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.Keywords
All Related Versions
Funding Information
- IITP (2015-0-00174)
- NRF (2018R1A5A1060031,2020R1C1C1014863)
This publication has 18 references indexed in Scilit:
- Image Super-Resolution by Neural Texture Transfer2019
- Fast Spatio-Temporal Residual Network for Video Super-Resolution2019
- CrossNet: An End-to-End Reference-Based Super Resolution Network Using Cross-Scale Warping2018
- Frame-Recurrent Video Super-Resolution2018
- Optical Flow Estimation Using a Spatial Pyramid Network2017
- Deep Laplacian Pyramid Networks for Fast and Accurate Super-Resolution2017
- Video Super-Resolution via Bidirectional Recurrent Convolutional NetworksIEEE Transactions on Pattern Analysis and Machine Intelligence, 2017
- Learning Cross-scale Correspondence and Patch-based Synthesis for Reference-based Super-Resolution2017
- Improving resolution and depth-of-field of light field cameras using a hybrid imaging system2014
- PatchMatchACM Transactions on Graphics, 2009