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

While learned video codecs have demonstrated great promise, they have yet toachieve sufficient efficiency for practical deployment. In this work, wepropose several novel ideas for learned video compression which allow forimproved performance for the low-latency mode (I- and P-frames only) along witha considerable increase in computational efficiency. In this setting, fornatural videos our approach compares favorably across the entire R-D curveunder metrics PSNR, MS-SSIM and VMAF against all mainstream video standards(H.264, H.265, AV1) and all ML codecs. At the same time, our approach runs atleast 5x faster and has fewer parameters than all ML codecs which report thesefigures.  Our contributions include a flexible-rate framework allowing a single modelto cover a large and dense range of bitrates, at a negligible increase incomputation and parameter count; an efficient backbone optimized for ML-basedcodecs; and a novel in-loop flow prediction scheme which leverages priorinformation towards more efficient compression.  We benchmark our method, which we call ELF-VC (Efficient, Learned andFlexible Video Coding) on popular video test sets UVG and MCL-JCV under metricsPSNR, MS-SSIM and VMAF. For example, on UVG under PSNR, it reduces the BD-rateby 44% against H.264, 26% against H.265, 15% against AV1, and 35% against thecurrent best ML codec. At the same time, on an NVIDIA Titan V GPU our approachencodes/decodes VGA at 49/91 FPS, HD 720 at 19/35 FPS, and HD 1080 at 10/18FPS.

ELF-VC: Efficient Learned Flexible-Rate Video Coding