publication . Conference object . 2019

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

Konstantinos Konstantoudakis; Emmanouil Christakis; Petros Drakoulis; Alexandros Doumanoglou; Nikolaos Zioulis; Dimitrios Zarpalas; Petros Daras;
Open Access English
  • Published: 20 May 2019
Abstract
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 trade-off. 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 neura...
Persistent Identifiers
Subjects
ACM Computing Classification System: Data_CODINGANDINFORMATIONTHEORYComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION
free text keywords: Video, Compression, Tele-Immersion, 3D Media Streaming, Performance Evaluation, JPEG, computer.file_format, computer, Transform coding, Convolutional neural network, Image compression, JPEG 2000, Deep learning, Computer science, Compression ratio, Artificial intelligence, business.industry, business, Codec, Real-time computing
Funded by
EC| 5G-MEDIA
Project
5G-MEDIA
Programmable edge-to-cloud virtualization fabric for the 5G Media industry
  • Funder: European Commission (EC)
  • Project Code: 761699
  • Funding stream: H2020 | IA
Validated by funder
Download fromView all 3 versions
ZENODO
Conference object . 2018
Provider: ZENODO
http://xplorestaging.ieee.org/...
Conference object . 2019
Provider: Crossref
Any information missing or wrong?Report an Issue