Skip to main content

Research Repository

Advanced Search

Method for Efficient CPU-GPU Streaming for Walkthrough of Full Motion Lightfield Video

Chitalu, Floyd M.; Koniaris, Babis; Mitchell, Kenny

Authors

Floyd M. Chitalu

Babis Koniaris



Abstract

Lightfield video, as a high-dimensional function, is very demanding in terms of storage. As such, lightfield video data, even in a compressed form, do not typically fit in GPU or main memory unless the capture area, resolution or duration is sufficiently small. Additionally, latency minimization--critical for viewer comfort in use-cases such as virtual reality--places further constraints in many compression schemes. In this paper, we propose a scalable method for streaming lightfield video, parameterized on viewer location and time, that efficiently handles RAM-to-GPU memory transfers of lightfield video in a compressed form, utilizing the GPU architecture for reduction of latency. We demonstrate the effectiveness of our method in a variety of compressed animated lightfield datasets.

Citation

Chitalu, F. M., Koniaris, B., & Mitchell, K. (2017, December). Method for Efficient CPU-GPU Streaming for Walkthrough of Full Motion Lightfield Video. Presented at 14th European Conference on Visual Media Production (CVMP 2017), London, United Kingdom

Presentation Conference Type Conference Paper (published)
Conference Name 14th European Conference on Visual Media Production (CVMP 2017)
Start Date Dec 11, 2017
End Date Dec 13, 2017
Publication Date 2017-12
Deposit Date Mar 3, 2020
Publisher Association for Computing Machinery (ACM)
Book Title CVMP 2017: Proceedings of the 14th European Conference on Visual Media Production (CVMP 2017)
ISBN 9781450353298
DOI https://doi.org/10.1145/3150165.3150173
Public URL http://researchrepository.napier.ac.uk/Output/2606347