An immersive video experience with real-time view synthesis leveraging the upcoming MPEG-I distribution format



An immersive video experience with real-time view synthesis leveraging the upcoming MPEG-I distribution format

An immersive video experience with real-time view synthesis leveraging the upcoming MPEG-I distribution format
Research Paper / ICME 2020 / Jul 2020 / Video coding, Immersive / AR/VR/MR

The upcoming MPEG Immersive Video (MIV) standard will enable storage and distribution of immersive video content over existing and future networks, for playback with 6 full or partial degrees of freedom of view position and orientation. The demo showcases a VOD server streaming MIV encoded immersive video contents up to a decoding client where an HMD is connected. The user can perceive the parallax as he moves his head (translation, rotation) when seated. The core contribution of the demo is a real-time GPU implementation of the virtual view synthesis at decoder side. An enhanced quality of rendered views is attained through a weighting strategy of source views contributions which leverages standardized metadata conveying information on the pruning decisions at encoder side.

Download Now


Related Content

Synergies between in-loop and out-of-loop mapping for HDR-PQ content
RESEARCH PAPER / Mar 2022 / HDR, Video Coding
This paper presents experimentation results related to adaptive video content mapping used as compression tool of HDR-PQ content. The purpose of adaptive video content mapping is to adapt the video signal dynamically depending on its statistical properties in order to better exploit the signal codewords range. Adaptive video content mapping...
Data-Driven Low-Rank Neural Network Compression
RESEARCH PAPER / Sep 2021 / Video coding, Compression, Machine learning/ Deep learning /Artificial Intelligence Neural network
Despite many modern applications of Deep Neural Networks (DNNs), the large number of parameters in the hidden layers makes them unattractive for deployment on devices with storage capacity constraints. In this paper we propose a Data-Driven Low-rank (DDLR) method to reduce the number of parameters of pretrained DNNs and expedite...
Compact and Adaptive Multiplane Images for View Synthesis
RESEARCH PAPER / Sep 2021 / Video coding, Machine learning/ Deep learning /Artificial Intelligence, Image processing, Computer Graphics
Recently, learning methods have been designed to create Multiplane Images (MPIs) for view synthesis. While MPIs are extremely powerful and facilitate high quality renderings, a great amount of memory is required, making them impractical for many applications. In this paper, we propose a learning method that optimizes the available memory...
Unpacking the Layers of AI Impact in 5G
WEBINAR / Feb 2023
Getting tough on patent holdout – Time for solutions
WEBINAR / Dec 2022
InterDigital: 5G Networking and the New Coding Stand...
WEBINAR / Oct 2022
InterDigital Honors Outstanding Inventors Shaping Wi...
BLOG / Feb 2023 / Posted By: InterDigital Comms
How patent holdout is moving up the agenda
BLOG / Feb 2023 / Posted By: InterDigital Comms
InterDigital confirmed as one of the world’s leading...
BLOG / Jan 2023 / Posted By: InterDigital Comms

ready to
learn more?

CONTACT INVESTORS
InterDigital logo in white

   © COPYRIGHT 2023 INTERDIGITAL, INC. ALL RIGHTS RESERVED.