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

Frame interpolation attempts to synthesise frames given one or moreconsecutive video frames. In recent years, deep learning approaches, andnotably convolutional neural networks, have succeeded at tackling low- andhigh-level computer vision problems including frame interpolation. Thesetechniques often tackle two problems, namely algorithm efficiency andreconstruction quality. In this paper, we present a multi-scale generativeadversarial network for frame interpolation (\mbox{FIGAN}). To maximise theefficiency of our network, we propose a novel multi-scale residual estimationmodule where the predicted flow and synthesised frame are constructed in acoarse-to-fine fashion. To improve the quality of synthesised intermediatevideo frames, our network is jointly supervised at different levels with aperceptual loss function that consists of an adversarial and two contentlosses. We evaluate the proposed approach using a collection of 60fps videosfrom YouTube-8m. Our results improve the state-of-the-art accuracy and providesubjective visual quality comparable to the best performing interpolationmethod at x47 faster runtime.

Frame Interpolation with Multi-Scale Deep Loss Functions and Generative Adversarial Networks