ADAPTIVEFUSION: Low Power Scene Reconstruction

Muhammad Huzaifa, Boyuan Tian, Yihan Pang, Henry Che, Shenlong Wang, Sarita Adve

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Towards deploying scene reconstruction on mobile devices with a stringent power budget, we propose ADAPTIVEFUSION to meet the power envelope by dynamically changing the reconstruction frequency while maintaining acceptable quality. Compared to a standard 30 Hz baseline, ADAPTIVEFUSION reduces frequency, and thus power, by 4.9 × on average and is applicable to other fusion-based algorithms.

Original languageEnglish (US)
Title of host publicationProceedings - 2023 IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops, VRW 2023
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages907-908
Number of pages2
ISBN (Electronic)9798350348392
DOIs
StatePublished - 2023
Event2023 IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops, VRW 2023 - Shanghai, China
Duration: Mar 25 2023Mar 29 2023

Publication series

NameProceedings - 2023 IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops, VRW 2023

Conference

Conference2023 IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops, VRW 2023
Country/TerritoryChina
CityShanghai
Period3/25/233/29/23

Keywords

  • Human-centered computing
  • Human-centered computing
  • Mixed/augmented reality
  • Virtual reality

ASJC Scopus subject areas

  • Computer Graphics and Computer-Aided Design
  • Computer Science Applications
  • Human-Computer Interaction
  • Media Technology

Fingerprint

Dive into the research topics of 'ADAPTIVEFUSION: Low Power Scene Reconstruction'. Together they form a unique fingerprint.

Cite this