SGER: A Domain-Model Approach to Reconstruction of 3-D Environments for Virtual Reality

IRI-9520434，华盛顿大学琳达·G·夏皮罗，50,000-12个月。SGER：一种用于虚拟现实的3D环境重建的领域模型方法该奖项为探索性研究小额拨款模式。从传感数据重建三维环境是一个计算机视觉问题，在虚拟现实和其他视觉信息系统领域有着重要的应用。虚拟现实相对较新的研究领域需要整个环境的3D模型，这对计算机视觉提出了几个重大的新挑战，包括处理场景中多个运动对象的能力，关于颜色和纹理的信息的集成，以及需要密切关注领域约束，以改进环境的3D模型的重建。本研究的新方法是利用领域知识来简化和改进三维环境获取过程。这种方法是知识驱动的，并试图了解环境的物理结构和环境中各个物体的物理结构。该奖项支持初步研究，以探索开发定义特定领域的物理约束的物理域模型的可行性。此类模型可能包括有关可能的3D曲面类别、可能的材质、曲面关系、常见的3D基本体、3D基本体之间的函数关系以及固定或受约束的光源的信息。

IRI-9520434 Shapiro, Linda G. University of Washington $50,000 - 12 mos. SGER: A Domain-Model Approach to Reconstruction of 3D Environments for Virtual Reality This award is in the Small Grants for Exploratory Research mode. Reconstruction of 3D environments from sensed data is a computer vision problem with important application to the area of virtual reality and other visual information systems. The relatively new research area of virtual reality requires 3D models of entire environments, and presents several significant new challenges for computer vision, including the ability to deal with multiple moving objects in the scene, integration of information about color and textures, and the need for close attention to domain constraints, to improve the reconstruction of a 3-D model of the environment. The new approach in this research is to use domain knowledge to simplify and improve the 3D environment-acquisition process. This approach is knowledge-driven and attempts to understand the physical structure of the environment and of the individual objects in the environment. This award supports preliminary research to explore the feasibility of development of physical domain models that define the physical constraints of a particular domain. Such models might include information about possible 3D surface classes, possible materials, surface relationships, common 3D primitive solids, functional relationships among the 3D primitives, and fixed or constrained lighting.