Panoramic scene generation from multi-view images with close foreground objects

Soon Young Lee, Jae Young Sim, Chang-Su Kim, Sang Uk Lee

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

3 Citations (Scopus)

Abstract

An algorithm to generate a panorama from multi-view images, which contain foreground objects with varying depths, is proposed in this work. The proposed algorithm constructs a foreground panorama and a background panorama separately, and then merges them into a complete panorama. First, the foreground panorama is obtained by finding the translational displacements of objects between source images. Second, the background panorama is initialized using warped source images and then optimized to preserve spatial consistency and satisfy visual constraints. Then, the background panorama is extended by inserting seams and merged with the foreground panorama. Experimental results demonstrate that the proposed algorithm provides visually satisfying panoramas with all meaningful foreground objects, but without severe artifacts in the backgrounds.

Original languageEnglish
Title of host publication28th Picture Coding Symposium, PCS 2010
Pages486-489
Number of pages4
DOIs
Publication statusPublished - 2010 Dec 1
Event28th Picture Coding Symposium, PCS 2010 - Nagoya, Japan
Duration: 2010 Dec 82010 Dec 10

Other

Other28th Picture Coding Symposium, PCS 2010
CountryJapan
CityNagoya
Period10/12/810/12/10

Keywords

  • 3D scene representation
  • Image panorama
  • Multi-view image processing
  • View expansion

ASJC Scopus subject areas

  • Computer Graphics and Computer-Aided Design
  • Computer Vision and Pattern Recognition

Cite this

Lee, S. Y., Sim, J. Y., Kim, C-S., & Lee, S. U. (2010). Panoramic scene generation from multi-view images with close foreground objects. In 28th Picture Coding Symposium, PCS 2010 (pp. 486-489). [5702543] https://doi.org/10.1109/PCS.2010.5702543

Panoramic scene generation from multi-view images with close foreground objects. / Lee, Soon Young; Sim, Jae Young; Kim, Chang-Su; Lee, Sang Uk.

28th Picture Coding Symposium, PCS 2010. 2010. p. 486-489 5702543.

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

Lee, SY, Sim, JY, Kim, C-S & Lee, SU 2010, Panoramic scene generation from multi-view images with close foreground objects. in 28th Picture Coding Symposium, PCS 2010., 5702543, pp. 486-489, 28th Picture Coding Symposium, PCS 2010, Nagoya, Japan, 10/12/8. https://doi.org/10.1109/PCS.2010.5702543
Lee SY, Sim JY, Kim C-S, Lee SU. Panoramic scene generation from multi-view images with close foreground objects. In 28th Picture Coding Symposium, PCS 2010. 2010. p. 486-489. 5702543 https://doi.org/10.1109/PCS.2010.5702543
Lee, Soon Young ; Sim, Jae Young ; Kim, Chang-Su ; Lee, Sang Uk. / Panoramic scene generation from multi-view images with close foreground objects. 28th Picture Coding Symposium, PCS 2010. 2010. pp. 486-489
@inproceedings{5f8565ef56cd4cb5bf82cc58cb9ef40f,
title = "Panoramic scene generation from multi-view images with close foreground objects",
abstract = "An algorithm to generate a panorama from multi-view images, which contain foreground objects with varying depths, is proposed in this work. The proposed algorithm constructs a foreground panorama and a background panorama separately, and then merges them into a complete panorama. First, the foreground panorama is obtained by finding the translational displacements of objects between source images. Second, the background panorama is initialized using warped source images and then optimized to preserve spatial consistency and satisfy visual constraints. Then, the background panorama is extended by inserting seams and merged with the foreground panorama. Experimental results demonstrate that the proposed algorithm provides visually satisfying panoramas with all meaningful foreground objects, but without severe artifacts in the backgrounds.",
keywords = "3D scene representation, Image panorama, Multi-view image processing, View expansion",
author = "Lee, {Soon Young} and Sim, {Jae Young} and Chang-Su Kim and Lee, {Sang Uk}",
year = "2010",
month = "12",
day = "1",
doi = "10.1109/PCS.2010.5702543",
language = "English",
isbn = "9781424471348",
pages = "486--489",
booktitle = "28th Picture Coding Symposium, PCS 2010",

}

TY - GEN

T1 - Panoramic scene generation from multi-view images with close foreground objects

AU - Lee, Soon Young

AU - Sim, Jae Young

AU - Kim, Chang-Su

AU - Lee, Sang Uk

PY - 2010/12/1

Y1 - 2010/12/1

N2 - An algorithm to generate a panorama from multi-view images, which contain foreground objects with varying depths, is proposed in this work. The proposed algorithm constructs a foreground panorama and a background panorama separately, and then merges them into a complete panorama. First, the foreground panorama is obtained by finding the translational displacements of objects between source images. Second, the background panorama is initialized using warped source images and then optimized to preserve spatial consistency and satisfy visual constraints. Then, the background panorama is extended by inserting seams and merged with the foreground panorama. Experimental results demonstrate that the proposed algorithm provides visually satisfying panoramas with all meaningful foreground objects, but without severe artifacts in the backgrounds.

AB - An algorithm to generate a panorama from multi-view images, which contain foreground objects with varying depths, is proposed in this work. The proposed algorithm constructs a foreground panorama and a background panorama separately, and then merges them into a complete panorama. First, the foreground panorama is obtained by finding the translational displacements of objects between source images. Second, the background panorama is initialized using warped source images and then optimized to preserve spatial consistency and satisfy visual constraints. Then, the background panorama is extended by inserting seams and merged with the foreground panorama. Experimental results demonstrate that the proposed algorithm provides visually satisfying panoramas with all meaningful foreground objects, but without severe artifacts in the backgrounds.

KW - 3D scene representation

KW - Image panorama

KW - Multi-view image processing

KW - View expansion

UR - http://www.scopus.com/inward/record.url?scp=79951778388&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79951778388&partnerID=8YFLogxK

U2 - 10.1109/PCS.2010.5702543

DO - 10.1109/PCS.2010.5702543

M3 - Conference contribution

SN - 9781424471348

SP - 486

EP - 489

BT - 28th Picture Coding Symposium, PCS 2010

ER -