LAMP: 3D layered, adaptive-resolution, and multi-perspective panorama—a new scene representation

A compact visual representation, called the 3D layered, adaptive-resolution, and multi-perspective panorama (LAMP), is proposed for representing large-scale 3D scenes with large variations of depths and obvious occlusions. Two kinds of 3D LAMP representations are proposed: the relief-like LAMP and t...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Computer vision and image understanding Jg. 96; H. 3; S. 294 - 326
Hauptverfasser: Zhu, Zhigang, Hanson, Allen R.
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Elsevier Inc 01.12.2004
Schlagworte:
Epipolar plane image
Image-based modeling and rendering
Layered representation
Multi-image processing
Multi-resolution
Spatio–temporal image
Multi-resolution
Multi-image processing
Epipolar plane image
Spatio–temporal image
Image-based modeling and rendering
Layered representation
ISSN:1077-3142, 1090-235X
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:A compact visual representation, called the 3D layered, adaptive-resolution, and multi-perspective panorama (LAMP), is proposed for representing large-scale 3D scenes with large variations of depths and obvious occlusions. Two kinds of 3D LAMP representations are proposed: the relief-like LAMP and the image-based LAMP. Both types of LAMPs concisely represent almost all the information from a long image sequence. Methods to construct LAMP representations from video sequences with dominant translation are provided. The relief-like LAMP is basically a single extended multi-perspective panoramic view image. Each pixel has a pair of texture and depth values, but each pixel may also have multiple pairs of texture-depth values to represent occlusion in layers, in addition to adaptive resolution changing with depth. The image-based LAMP, on the other hand, consists of a set of multi-perspective layers, each of which has a pair of 2D texture and depth maps, but with adaptive time-sampling scales depending on depths of scene points. Several examples of 3D LAMP construction for real image sequences are given. The 3D LAMP is a concise and powerful representation for image-based rendering.
ISSN:1077-3142
1090-235X
DOI:10.1016/j.cviu.2004.03.011