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

### Dublin Core Export

<?xml version='1.0' encoding='utf-8'?>
<oai_dc:dc xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:oai_dc="http://www.openarchives.org/OAI/2.0/oai_dc/" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/oai_dc/ http://www.openarchives.org/OAI/2.0/oai_dc.xsd">
<dc:creator>Konstantoudakis, Konstantinos</dc:creator>
<dc:creator>Christakis, Emmanouil</dc:creator>
<dc:creator>Drakoulis, Petros</dc:creator>
<dc:creator>Doumanoglou, Alexandros</dc:creator>
<dc:creator>Zioulis, Nikolaos</dc:creator>
<dc:creator>Zarpalas, Dimitrios</dc:creator>
<dc:creator>Daras, Petros</dc:creator>
<dc:date>2018-11-26</dc:date>
<dc:description>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.</dc:description>
<dc:identifier>https://zenodo.org/record/3137854</dc:identifier>
<dc:identifier>10.1109/SITIS.2018.00022</dc:identifier>
<dc:identifier>oai:zenodo.org:3137854</dc:identifier>
<dc:language>eng</dc:language>
<dc:relation>info:eu-repo/grantAgreement/EC/H2020/761699/</dc:relation>
<dc:rights>info:eu-repo/semantics/openAccess</dc:rights>
<dc:subject>Video</dc:subject>
<dc:subject>Compression</dc:subject>
<dc:subject>Tele-Immersion</dc:subject>
<dc:subject>3D Media Streaming</dc:subject>
<dc:subject>Performance Evaluation</dc:subject>
<dc:title>Comparing CNNs and JPEG for Real-Time Multi-view Streaming in Tele-Immersive Scenarios</dc:title>
<dc:type>info:eu-repo/semantics/conferencePaper</dc:type>
<dc:type>publication-conferencepaper</dc:type>
</oai_dc:dc>

34
32
views