Real-time Illumination Estimation for Mixed Reality on Mobile Devices

Di Xu, Zhen Li, Yanning Zhang

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

7 Scopus citations

Abstract

We present a lightweight lighting estimation method for the purpose of realistic mixed reality (MR) on mobile devices. Given a single RGB image, our method estimates the environment lighting and renders the virtual object in real-time. While previous works tackled this problem by reconstructing the complicated high dynamic range (HDR) environment maps, our deep neural network directly infers the corresponding spherical harmonics in extensive environments. Compared to previous approaches, our method is more robust and efficient as it works for both indoor and outdoor scenes in real-time. Experiments show that our approach achieves realistic rendering in various MR scenarios.

Original languageEnglish
Title of host publicationProceedings - 2020 IEEE Conference on Virtual Reality and 3D User Interfaces, VRW 2020
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages703-704
Number of pages2
ISBN (Electronic)9781728165325
DOIs
StatePublished - Mar 2020
Event2020 IEEE Conference on Virtual Reality and 3D User Interfaces, VRW 2020 - Atlanta, United States
Duration: 22 Mar 202026 Mar 2020

Publication series

NameProceedings - 2020 IEEE Conference on Virtual Reality and 3D User Interfaces, VRW 2020

Conference

Conference2020 IEEE Conference on Virtual Reality and 3D User Interfaces, VRW 2020
Country/TerritoryUnited States
CityAtlanta
Period22/03/2026/03/20

Keywords

  • Computer Graphics
  • Computing methodologies
  • Graphics systems and interface
  • Mixed / augmented reality

Fingerprint

Dive into the research topics of 'Real-time Illumination Estimation for Mixed Reality on Mobile Devices'. Together they form a unique fingerprint.

Cite this