Generative adversarial network based image blur compensation for projection-based mixed reality

Yuta Kageyama, Mariko Isogawa, Daisuke Iwai, Kosuke Sato

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

Abstract

Projection-based mixed reality superimposes an image on a real object by a projector. There is a problem that spatially nonuniform blurring occurs in the projected result due to defocus blur and subsurface scattering. As the solution, some methods of applying blur compensation to an input image before projecting have been studied. In this paper, we propose to use a generative adversarial network (GAN) that computes the compensation image from an input image and a projected result.

Original languageEnglish
Title of host publication2019 IEEE 8th Global Conference on Consumer Electronics, GCCE 2019
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages227-228
Number of pages2
ISBN (Electronic)9781728135755
DOIs
Publication statusPublished - 2019 Oct
Externally publishedYes
Event8th IEEE Global Conference on Consumer Electronics, GCCE 2019 - Osaka, Japan
Duration: 2019 Oct 152019 Oct 18

Publication series

Name2019 IEEE 8th Global Conference on Consumer Electronics, GCCE 2019

Conference

Conference8th IEEE Global Conference on Consumer Electronics, GCCE 2019
Country/TerritoryJapan
CityOsaka
Period19/10/1519/10/18

Keywords

  • Blur compensation
  • Convolutional neural network (CNN)
  • Generative adversarial network (GAN)
  • Projection-based mixed reality

ASJC Scopus subject areas

  • Instrumentation
  • Artificial Intelligence
  • Computer Networks and Communications
  • Computer Science Applications
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'Generative adversarial network based image blur compensation for projection-based mixed reality'. Together they form a unique fingerprint.

Cite this