Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

Compacting Singleshot Multi-Plane Image via Scale Adjustment

Bergfelt, Max ; Larsson, Viktor LU ; Saito, Hideo and Mori, Shohei (2023) 2023 IEEE International Symposium on Mixed and Augmented Reality Adjunct, ISMAR-Adjunct 2023 p.549-554
Abstract

A recent singleshot multiplane image (MPI) generation enables to copy an observed reality within a camera frame into other reality domains via view synthesis. While the scene scale is unknown due to the nature of singleshot MPI processing, camera tracking algorithms can estimate depth within the application world coordinate system. Given such depth information, we propose to adjust the scale of singleshot MPI to that of the currently observed scene. We find the individual scales of the MPI layers by minimizing the differences between the depth of MPI rendering and that of camera tracking. We eventually found that many layers fall within a close depth. Therefore, we merge such layers into one to compact the MPI representation. We... (More)

A recent singleshot multiplane image (MPI) generation enables to copy an observed reality within a camera frame into other reality domains via view synthesis. While the scene scale is unknown due to the nature of singleshot MPI processing, camera tracking algorithms can estimate depth within the application world coordinate system. Given such depth information, we propose to adjust the scale of singleshot MPI to that of the currently observed scene. We find the individual scales of the MPI layers by minimizing the differences between the depth of MPI rendering and that of camera tracking. We eventually found that many layers fall within a close depth. Therefore, we merge such layers into one to compact the MPI representation. We compared our method with baselines using real and synthetic datasets with dense and sparse depth inputs. Our results demonstrate that our algorithm achieves higher scores in image metrics and reduces MPI data amount by up to 78%.

(Less)
Please use this url to cite or link to this publication:
author
; ; and
organization
publishing date
type
Chapter in Book/Report/Conference proceeding
publication status
published
subject
keywords
Computer graphics, Computing methodologies, Human computer interaction (HCI), Human-centered computing, Image manipulation, Image-based rendering, Interaction paradigms, Mixed / augmented reality
host publication
Proceedings - 2023 IEEE International Symposium on Mixed and Augmented Reality Adjunct, ISMAR-Adjunct 2023
editor
Bruder, Gerd ; Olivier, Anne-Helene ; Cunningham, Andrew ; Peng, Evan Yifan ; Grubert, Jens and Williams, Ian
pages
6 pages
publisher
IEEE - Institute of Electrical and Electronics Engineers Inc.
conference name
2023 IEEE International Symposium on Mixed and Augmented Reality Adjunct, ISMAR-Adjunct 2023
conference location
Sydney, Australia
conference dates
2023-10-16 - 2023-10-20
external identifiers
  • scopus:85180366446
ISBN
9798350328912
DOI
10.1109/ISMAR-Adjunct60411.2023.00117
language
English
LU publication?
yes
id
0add2310-16d7-40e5-8ca3-39918594b5fe
date added to LUP
2024-01-10 15:25:04
date last changed
2024-01-10 15:26:53
@inproceedings{0add2310-16d7-40e5-8ca3-39918594b5fe,
  abstract     = {{<p>A recent singleshot multiplane image (MPI) generation enables to copy an observed reality within a camera frame into other reality domains via view synthesis. While the scene scale is unknown due to the nature of singleshot MPI processing, camera tracking algorithms can estimate depth within the application world coordinate system. Given such depth information, we propose to adjust the scale of singleshot MPI to that of the currently observed scene. We find the individual scales of the MPI layers by minimizing the differences between the depth of MPI rendering and that of camera tracking. We eventually found that many layers fall within a close depth. Therefore, we merge such layers into one to compact the MPI representation. We compared our method with baselines using real and synthetic datasets with dense and sparse depth inputs. Our results demonstrate that our algorithm achieves higher scores in image metrics and reduces MPI data amount by up to 78%.</p>}},
  author       = {{Bergfelt, Max and Larsson, Viktor and Saito, Hideo and Mori, Shohei}},
  booktitle    = {{Proceedings - 2023 IEEE International Symposium on Mixed and Augmented Reality Adjunct, ISMAR-Adjunct 2023}},
  editor       = {{Bruder, Gerd and Olivier, Anne-Helene and Cunningham, Andrew and Peng, Evan Yifan and Grubert, Jens and Williams, Ian}},
  isbn         = {{9798350328912}},
  keywords     = {{Computer graphics; Computing methodologies; Human computer interaction (HCI); Human-centered computing; Image manipulation; Image-based rendering; Interaction paradigms; Mixed / augmented reality}},
  language     = {{eng}},
  pages        = {{549--554}},
  publisher    = {{IEEE - Institute of Electrical and Electronics Engineers Inc.}},
  title        = {{Compacting Singleshot Multi-Plane Image via Scale Adjustment}},
  url          = {{http://dx.doi.org/10.1109/ISMAR-Adjunct60411.2023.00117}},
  doi          = {{10.1109/ISMAR-Adjunct60411.2023.00117}},
  year         = {{2023}},
}