Go to main content
Formats
Format
BibTeX
MARCXML
TextMARC
MARC
DublinCore
EndNote
NLM
RefWorks
RIS

Files

Abstract

Real-Time video solutions such as volumetric human telepresence require a degree of quality than cannot be guaranteed by existing solutions. In order to implement reinforcement learning in this context, programmable platforms are required for fast prototyping, evaluation and testing. We present a platform that can be used to develop and test more robust models with performance parameters that closely resemble real-world scenarios. We explore the components required to make such a platform viable, and we demonstrate the performance of the overall system.

Details

PDF

Statistics

from
to
Export
Download Full History