Conference paper Open Access

Comparing CNNs and JPEG for Real-Time Multi-view Streaming in Tele-Immersive Scenarios

Konstantoudakis, Konstantinos; Christakis, Emmanouil; Drakoulis, Petros; Doumanoglou, Alexandros; Zioulis, Nikolaos; Zarpalas, Dimitrios; Daras, Petros


DataCite XML Export

<?xml version='1.0' encoding='utf-8'?>
<resource xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns="http://datacite.org/schema/kernel-4" xsi:schemaLocation="http://datacite.org/schema/kernel-4 http://schema.datacite.org/meta/kernel-4.1/metadata.xsd">
  <identifier identifierType="URL">https://zenodo.org/record/3137854</identifier>
  <creators>
    <creator>
      <creatorName>Konstantoudakis, Konstantinos</creatorName>
      <givenName>Konstantinos</givenName>
      <familyName>Konstantoudakis</familyName>
      <affiliation>Centre for Research and Technology Hellas (CERTH), Information Technologies Institute (ITI)</affiliation>
    </creator>
    <creator>
      <creatorName>Christakis, Emmanouil</creatorName>
      <givenName>Emmanouil</givenName>
      <familyName>Christakis</familyName>
      <affiliation>Centre for Research and Technology Hellas (CERTH), Information Technologies Institute (ITI)</affiliation>
    </creator>
    <creator>
      <creatorName>Drakoulis, Petros</creatorName>
      <givenName>Petros</givenName>
      <familyName>Drakoulis</familyName>
      <nameIdentifier nameIdentifierScheme="ORCID" schemeURI="http://orcid.org/">0000-0003-3434-3290</nameIdentifier>
      <affiliation>Centre for Research and Technology Hellas (CERTH), Information Technologies Institute (ITI)</affiliation>
    </creator>
    <creator>
      <creatorName>Doumanoglou, Alexandros</creatorName>
      <givenName>Alexandros</givenName>
      <familyName>Doumanoglou</familyName>
      <nameIdentifier nameIdentifierScheme="ORCID" schemeURI="http://orcid.org/">0000-0002-4337-1720</nameIdentifier>
      <affiliation>Centre for Research and Technology Hellas (CERTH), Information Technologies Institute (ITI)</affiliation>
    </creator>
    <creator>
      <creatorName>Zioulis, Nikolaos</creatorName>
      <givenName>Nikolaos</givenName>
      <familyName>Zioulis</familyName>
      <nameIdentifier nameIdentifierScheme="ORCID" schemeURI="http://orcid.org/">0000-0002-7898-9344</nameIdentifier>
      <affiliation>Centre for Research and Technology Hellas (CERTH), Information Technologies Institute (ITI)</affiliation>
    </creator>
    <creator>
      <creatorName>Zarpalas, Dimitrios</creatorName>
      <givenName>Dimitrios</givenName>
      <familyName>Zarpalas</familyName>
      <affiliation>Centre for Research and Technology Hellas (CERTH), Information Technologies Institute (ITI)</affiliation>
    </creator>
    <creator>
      <creatorName>Daras, Petros</creatorName>
      <givenName>Petros</givenName>
      <familyName>Daras</familyName>
      <affiliation>Centre for Research and Technology Hellas (CERTH), Information Technologies Institute (ITI)</affiliation>
    </creator>
  </creators>
  <titles>
    <title>Comparing CNNs and JPEG for Real-Time Multi-view Streaming in Tele-Immersive Scenarios</title>
  </titles>
  <publisher>Zenodo</publisher>
  <publicationYear>2018</publicationYear>
  <subjects>
    <subject>Video</subject>
    <subject>Compression</subject>
    <subject>Tele-Immersion</subject>
    <subject>3D Media Streaming</subject>
    <subject>Performance Evaluation</subject>
  </subjects>
  <dates>
    <date dateType="Issued">2018-11-26</date>
  </dates>
  <language>en</language>
  <resourceType resourceTypeGeneral="Text">Conference paper</resourceType>
  <alternateIdentifiers>
    <alternateIdentifier alternateIdentifierType="url">https://zenodo.org/record/3137854</alternateIdentifier>
  </alternateIdentifiers>
  <relatedIdentifiers>
    <relatedIdentifier relatedIdentifierType="DOI" relationType="IsIdenticalTo">10.1109/SITIS.2018.00022</relatedIdentifier>
  </relatedIdentifiers>
  <rightsList>
    <rights rightsURI="http://creativecommons.org/licenses/by/4.0/legalcode">Creative Commons Attribution 4.0 International</rights>
    <rights rightsURI="info:eu-repo/semantics/openAccess">Open Access</rights>
  </rightsList>
  <descriptions>
    <description descriptionType="Abstract">&lt;p&gt;Deep learning-based codecs for lossy image compression have recently managed to surpass traditional codecs like JPEG and JPEG 2000 in terms of rate-distortion tradeoff. However, they generally utilize architectures with large numbers of stacked layers, often making their inference execution prohibitively slow for time-sensitive applications. In this work, we assess the suitability of such compression techniques in real-time video streaming, and, more specifically, next-generation interactive tele-presence applications, which impose stringent latency requirements. To that end, we compare a recently published work on image compression based on convolutional neural networks which achieves state-of-the-art compression ratio using a relatively lightweight architecture, against a CPU and a GPU implementation of JPEG, measuring compression ratios and timings. With these results, we run a simulation of a tele-immersion pipeline for various networking conditions and examine the performance of the compared codecs, calculating framerates and latencies for different codec/network combinations.&lt;/p&gt;</description>
  </descriptions>
  <fundingReferences>
    <fundingReference>
      <funderName>European Commission</funderName>
      <funderIdentifier funderIdentifierType="Crossref Funder ID">10.13039/501100000780</funderIdentifier>
      <awardNumber awardURI="info:eu-repo/grantAgreement/EC/H2020/761699/">761699</awardNumber>
      <awardTitle>Programmable edge-to-cloud virtualization fabric for the 5G Media industry</awardTitle>
    </fundingReference>
  </fundingReferences>
</resource>
34
32
views
downloads
Views 34
Downloads 32
Data volume 40.7 MB
Unique views 32
Unique downloads 28

Share

Cite as