Multiperspective modeling, rendering, and imaging
Multiperspective modeling, rendering, and imaging
复制标题
DOI：
10.1145/1508044.1508094
复制
发表时间：
2008-12
期刊：
影响因子：
--
通讯作者：
Jingyi Yu;L. McMillan;P. Sturm
中科院分区：
文献类型：
--
作者：
Jingyi Yu;L. McMillan;P. Sturm
透视图像表示场景中对象从单个视点出现时的空间关系。相比之下，多视角图像将从多个视点看到的内容组合成单个图像。尽管视图不协调，但有效的多视角图像能够保持空间连贯性，并且可以在单一上下文中描绘场景的细节，这些细节从单一视图中无法同时获得，但观看者可以轻松解释。在计算机视觉中，多视角图像已用于分析通过运动揭示的结构，并使用镜子生成具有宽视场的全景图像。在此 STAR 中，我们提供了有关多视角建模和渲染方法以及多视角成像系统主题的实用指南。我们首先简要回顾一下艺术家经常使用的多视角图像技术，例如埃舍尔的视觉悖论、毕加索和布拉克的立体主义以及赛璐珞动画中的多视角全景。然后，我们描述现有多视角相机模型的特征，重点关注其基础几何和图像属性。我们演示如何使用这些相机模型来创建特定的多视角渲染效果。此外，我们还展示了许多此类相机满足多视角立体约束，并且我们演示了几种用于提取计算机视觉 3D 几何形状的多视角成像系统。参与者将学习多视角建模和渲染主题，以生成引人注目的计算机图形图像，以及多视角成像主题，以提取计算机视觉的 3D 几何图形。我们希望提供足够的基础知识来满足技术专家的要求，同时又不会吓到对多视角图像感兴趣的好奇数字艺术家。目标受众包括数字艺术家、摄影师以及使用或构建多视角相机的计算机图形和计算机视觉研究人员。他们将学习多视角建模和渲染，以及许多现实世界的多视角成像系统。
A perspective image represents the spatial relationships of objects in a scene as they 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 are able to 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 for analyzing structure revealed via motion and generating panoramic images with a wide field-of-view using mirrors. In this STAR, we provide a practical guide on topics in multiperspective modeling and rendering methods and multiperspective imaging systems. We start with a brief review of multiperspective image techniques frequently employed by artists such as the visual paradoxes of Escher, the Cubism of Picasso and Braque, and multiperspective panoramas in cel animations. We then characterize existing multiperspective camera models, with an emphasis on their underlying geometry and image properties. We demonstrate how to use these camera models for creating specific multiperspective rendering effects. Furthermore, we show that many of these cameras satisfy the multiperspective stereo constraints and we demonstrate several multiperspective imaging systems for extracting 3D geometry for computer vision. The participants learn about topics in multiperspective modeling and rendering for generating compelling pictures for computer graphics and in multiperspective imaging for extracting 3D geometry for computer vision. We hope to provide enough fundamentals to satisfy the technical specialist without intimidating curious digital artists interested in multiperspective images. The intended audience includes digital artists, photographers, and computer graphics and computer vision researchers using or building multiperspective cameras. They will learn about multiperspective modeling and rendering, along with many real world multiperspective imaging systems.