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
Event28th Picture Coding Symposium, PCS 2010 - Nagoya, Japan
Duration: 2010 Dec 82010 Dec 10

Publication series

Name28th Picture Coding Symposium, PCS 2010

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