“Multiperspective Modeling, Rendering, and Imaging” by Yu
Conference:
Type(s):
Title:
- Multiperspective Modeling, Rendering, and Imaging
Presenter(s)/Author(s):
Abstract:
A perspective image represents the spatial relationships of objects in a scene as they would appear from a single viewpoint. In contrast, a multiperspective image combines what is seen from several viewpoints into a single image. Despite their incongruity of view, effective multiperspective images can preserve spatial coherence and can depict, within a single context, details of a scene that are simultaneously inaccessible from a single view, yet easily interpretable by a viewer. In computer vision, multiperspective images have been used to analyse structure revealed via motion and generate panoramic images with a wide field of view using mirrors.
This tutorial provides a practical guide on topics in multiperspective modeling and rendering methods, and multiperspective imaging systems. It begins with a brief review of multiperspective image techniques frequently employed by artists. Illustrations include the visual paradoxes of Escher, the Cubism of Picasso and Braque, and multiperspective panoramas in cel-animations. The course characterises existing multiperspective camera models, with an emphasis on their underlying geometry and image properties, then demonstrates how to use these camera models for creating specific multiperspective rendering effects. The course includes demonstrations of several multiperspective imaging systems for extracting 3D geometry for computer vision.
Additional Information:
Prerequisites
Basic understanding of camera operation, image processing, and machine vision.
Intended Audience
Digital artists, photographers, and computer graphics and computer vision researchers who use or build multiperspective cameras.
