Appearance-based virtual view generation of temporally-varying events from multi-camera images in the 3D room

Hideo Saito, Shigeyuki Baba, Makoto Kimura, Sundar Vedula, Takeo Kanade

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

39 Citations (Scopus)

Abstract

We present an "appearance based" virtual view generation method for temporally-varying events taken by multiple cameras of the "3D Room", developed by our group. With this method we can generate images from any virtual view point between two selected real views. The virtual appearance view generation method is based on simple interpolation between two selected views. The correspondence between the views are automatically generated from the multiple images by use of the volumetric model shape reconstruction framework. Since the correspondences are obtained by the recovered volumetric model, even occluded regions in the views can be correctly interpolated in the virtual view images. The virtual view image sequences are presented for demonstrating the performance of the virtual view image generation in the 3D Room.

Original languageEnglish
Title of host publicationProceedings - 2nd International Conference on 3-D Digital Imaging and Modeling, 3DIM 1999
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages516-525
Number of pages10
ISBN (Print)0769500625, 9780769500621
DOIs
Publication statusPublished - 1999 Jan 1
Externally publishedYes
Event2nd International Conference on 3-D Digital Imaging and Modeling, 3DIM 1999 - Ottawa, United States
Duration: 1999 Oct 41999 Oct 8

Other

Other2nd International Conference on 3-D Digital Imaging and Modeling, 3DIM 1999
CountryUnited States
CityOttawa
Period99/10/499/10/8

Fingerprint

rooms
Camera
Cameras
cameras
Interpolation
Correspondence
Shape Reconstruction
interpolation
Image Sequence
Interpolate
Model

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Modelling and Simulation
  • Instrumentation

Cite this

Saito, H., Baba, S., Kimura, M., Vedula, S., & Kanade, T. (1999). Appearance-based virtual view generation of temporally-varying events from multi-camera images in the 3D room. In Proceedings - 2nd International Conference on 3-D Digital Imaging and Modeling, 3DIM 1999 (pp. 516-525). [805384] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IM.1999.805384

Appearance-based virtual view generation of temporally-varying events from multi-camera images in the 3D room. / Saito, Hideo; Baba, Shigeyuki; Kimura, Makoto; Vedula, Sundar; Kanade, Takeo.

Proceedings - 2nd International Conference on 3-D Digital Imaging and Modeling, 3DIM 1999. Institute of Electrical and Electronics Engineers Inc., 1999. p. 516-525 805384.

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

Saito, H, Baba, S, Kimura, M, Vedula, S & Kanade, T 1999, Appearance-based virtual view generation of temporally-varying events from multi-camera images in the 3D room. in Proceedings - 2nd International Conference on 3-D Digital Imaging and Modeling, 3DIM 1999., 805384, Institute of Electrical and Electronics Engineers Inc., pp. 516-525, 2nd International Conference on 3-D Digital Imaging and Modeling, 3DIM 1999, Ottawa, United States, 99/10/4. https://doi.org/10.1109/IM.1999.805384
Saito H, Baba S, Kimura M, Vedula S, Kanade T. Appearance-based virtual view generation of temporally-varying events from multi-camera images in the 3D room. In Proceedings - 2nd International Conference on 3-D Digital Imaging and Modeling, 3DIM 1999. Institute of Electrical and Electronics Engineers Inc. 1999. p. 516-525. 805384 https://doi.org/10.1109/IM.1999.805384
Saito, Hideo ; Baba, Shigeyuki ; Kimura, Makoto ; Vedula, Sundar ; Kanade, Takeo. / Appearance-based virtual view generation of temporally-varying events from multi-camera images in the 3D room. Proceedings - 2nd International Conference on 3-D Digital Imaging and Modeling, 3DIM 1999. Institute of Electrical and Electronics Engineers Inc., 1999. pp. 516-525
@inproceedings{bab7184c0e5d44bd80f307821b3277c7,
title = "Appearance-based virtual view generation of temporally-varying events from multi-camera images in the 3D room",
abstract = "We present an {"}appearance based{"} virtual view generation method for temporally-varying events taken by multiple cameras of the {"}3D Room{"}, developed by our group. With this method we can generate images from any virtual view point between two selected real views. The virtual appearance view generation method is based on simple interpolation between two selected views. The correspondence between the views are automatically generated from the multiple images by use of the volumetric model shape reconstruction framework. Since the correspondences are obtained by the recovered volumetric model, even occluded regions in the views can be correctly interpolated in the virtual view images. The virtual view image sequences are presented for demonstrating the performance of the virtual view image generation in the 3D Room.",
author = "Hideo Saito and Shigeyuki Baba and Makoto Kimura and Sundar Vedula and Takeo Kanade",
year = "1999",
month = "1",
day = "1",
doi = "10.1109/IM.1999.805384",
language = "English",
isbn = "0769500625",
pages = "516--525",
booktitle = "Proceedings - 2nd International Conference on 3-D Digital Imaging and Modeling, 3DIM 1999",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Appearance-based virtual view generation of temporally-varying events from multi-camera images in the 3D room

AU - Saito, Hideo

AU - Baba, Shigeyuki

AU - Kimura, Makoto

AU - Vedula, Sundar

AU - Kanade, Takeo

PY - 1999/1/1

Y1 - 1999/1/1

N2 - We present an "appearance based" virtual view generation method for temporally-varying events taken by multiple cameras of the "3D Room", developed by our group. With this method we can generate images from any virtual view point between two selected real views. The virtual appearance view generation method is based on simple interpolation between two selected views. The correspondence between the views are automatically generated from the multiple images by use of the volumetric model shape reconstruction framework. Since the correspondences are obtained by the recovered volumetric model, even occluded regions in the views can be correctly interpolated in the virtual view images. The virtual view image sequences are presented for demonstrating the performance of the virtual view image generation in the 3D Room.

AB - We present an "appearance based" virtual view generation method for temporally-varying events taken by multiple cameras of the "3D Room", developed by our group. With this method we can generate images from any virtual view point between two selected real views. The virtual appearance view generation method is based on simple interpolation between two selected views. The correspondence between the views are automatically generated from the multiple images by use of the volumetric model shape reconstruction framework. Since the correspondences are obtained by the recovered volumetric model, even occluded regions in the views can be correctly interpolated in the virtual view images. The virtual view image sequences are presented for demonstrating the performance of the virtual view image generation in the 3D Room.

UR - http://www.scopus.com/inward/record.url?scp=85037695474&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85037695474&partnerID=8YFLogxK

U2 - 10.1109/IM.1999.805384

DO - 10.1109/IM.1999.805384

M3 - Conference contribution

SN - 0769500625

SN - 9780769500621

SP - 516

EP - 525

BT - Proceedings - 2nd International Conference on 3-D Digital Imaging and Modeling, 3DIM 1999

PB - Institute of Electrical and Electronics Engineers Inc.

ER -