English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

In this paper, we address the space-time video super-resolution, which aimsat generating a high-resolution (HR) slow-motion video from a low-resolution(LR) and low frame rate (LFR) video sequence. A na\"ive method is to decomposeit into two sub-tasks: video frame interpolation (VFI) and videosuper-resolution (VSR). Nevertheless, temporal interpolation and spatialupscaling are intra-related in this problem. Two-stage approaches cannot fullymake use of this natural property. Besides, state-of-the-art VFI or VSR deepnetworks usually have a large frame reconstruction module in order to obtainhigh-quality photo-realistic video frames, which makes the two-stage approacheshave large models and thus be relatively time-consuming. To overcome theissues, we present a one-stage space-time video super-resolution framework,which can directly reconstruct an HR slow-motion video sequence from an inputLR and LFR video. Instead of reconstructing missing LR intermediate frames asVFI models do, we temporally interpolate LR frame features of the missing LRframes capturing local temporal contexts by a feature temporal interpolationmodule. Extensive experiments on widely used benchmarks demonstrate that theproposed framework not only achieves better qualitative and quantitativeperformance on both clean and noisy LR frames but also is several times fasterthan recent state-of-the-art two-stage networks. The source code is released inhttps://github.com/Mukosame/Zooming-Slow-Mo-CVPR-2020 .

Zooming SlowMo: An Efficient One-Stage Framework for Space-Time Video Super-Resolution