"Panorama completion for street views" by Zhe Zhu, Ralph R. Martin et al.

Article Title

Authors

Zhe Zhu, TNLIST, Department of Computer Science and Technology, Tsinghua University, Beijing 100084, China.
Ralph R. Martin, School of Computer Science & Informatics, Cardiff University, UK.
Shi-Min Hu, TNLIST, Department of Computer Science and Technology, Tsinghua University, Beijing 100084, China.

Keywords

image completion, panorama, street views, structure-rectifying warp

Abstract

This paper considers panorama images used for street views. Their viewing angle of 360∘ causes pixels at the top and bottom to appear stretched and warped. Although current image completion algorithms work well, they cannot be directly used in the presence of such distortions found in panoramas of street views. We thus propose a novel approach to complete such 360∘ panoramas using optimization-based projection to deal with distortions. Experimental results show that our approach is efficient and provides an improvement over standard image completion algorithms.