Poster: Reliable 3D Reconstruction for Ad-hoc Edge Implementations

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Absur, Md Nurul, Brahma, Swastik, Debroy, Saptarshi
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912120919031808
author Absur, Md Nurul
Brahma, Swastik
Debroy, Saptarshi
author_facet Absur, Md Nurul
Brahma, Swastik
Debroy, Saptarshi
contents Ad-hoc edge deployments to support real-time complex video processing applications such as, multi-view 3D reconstruction often suffer from spatio-temporal system disruptions that greatly impact reconstruction quality. In this poster paper, we present a novel portfolio theory-inspired edge resource management strategy to ensure reliable multi-view 3D reconstruction by accounting for possible system disruptions.
format Preprint
id arxiv_https___arxiv_org_abs_2411_10705
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Poster: Reliable 3D Reconstruction for Ad-hoc Edge Implementations
Absur, Md Nurul
Brahma, Swastik
Debroy, Saptarshi
Computer Vision and Pattern Recognition
Ad-hoc edge deployments to support real-time complex video processing applications such as, multi-view 3D reconstruction often suffer from spatio-temporal system disruptions that greatly impact reconstruction quality. In this poster paper, we present a novel portfolio theory-inspired edge resource management strategy to ensure reliable multi-view 3D reconstruction by accounting for possible system disruptions.
title Poster: Reliable 3D Reconstruction for Ad-hoc Edge Implementations
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2411.10705