Image-based modeling and lighting
Image-based modeling and lighting
复制标题
基于图像的建模和照明
DOI：
10.1145/345370.345406
复制
发表时间：
1999
期刊：
影响因子：
--
通讯作者：
P. Debevec
中科院分区：
文献类型：
--
作者：
P. Debevec
也许计算机图形学发展中最突出的主线是对逼真图像的追求。从 20 世纪 60 年代的矢量图形开始，图形界逐渐开发出更先进的显示硬件、几何表示、表面反射率模型和照明算法，到 90 年代照片级真实感渲染已成为传统计算机图形学的一部分。虽然现在可以使用传统的计算机图形来实现逼真的渲染，但它们通常并不容易实现。首先，创建逼真的模型是一项时间和人才密集型的任务。对于大多数软件，美术师需要一块一块地构建详细的模型，然后指定场景中所有各种表面的反射特性（颜色、纹理、镜面反射等）。其次，生成逼真的渲染需要先进的技术，例如光能传递和全局照明，这些技术往往需要大量的计算。简而言之，建模往往很困难，而且渲染速度很慢。对于室内设计、建筑规划、模拟、虚拟博物馆和文化遗产等应用，人们希望使用计算机渲染的物体和环境通常存在于现实世界中。在这种情况下，建模和渲染的挑战会大大增加：由于人们熟悉结果应该是什么样子，他们会对结果的质量抱有更高的期望。然而，现实世界中的物体和环境也有一个非常有用的特性：它们可以被拍照。此外，在过去几年中，人们进行了大量的研究来对照片中的物体和场景的几何形状和外观进行建模。计算机视觉涉及算法的开发，以从数字图像中获取各种信息。从 2D 照片恢复 3D 结构的过程（现在称为基于图像的建模）一直是其核心工作之一。相反，从图像和几何图形逼真地渲染对象和场景的过程称为基于图像的渲染。由于模型来自照片，因此建模不必很困难，并且由于阴影也来自图像，因此渲染不必很慢。在接下来的几节中，我将讨论许多基于图像的建模技术以及一些将它们与基于图像的渲染结合使用的项目。
Perhaps the most prominent thread in the development of computer graphics has been the pursuit of photorealistic imagery. Starting from the vector graphics of the 1960s, the graphics community has developed progressively more advanced display hardware, geometr ic representat ions, surface reflectance models and i l lumination algorithms, and by the 1990s photoreal is t ic rendering has become a part of traditional computer graphics. While photorealistic renderings can now be achieved wi th t rad i t iona l computer graphics, they general ly do not come easily. First, creating realistic models is a time and talent-intensive task.With most software, the artist needs to build a detailed model piece by piece, and then specify the reflectance characteristics (color, texture, speculari~/, etc.) for all the various surfaces in the scene. Second, generating photorealistic renderings requires advanced techniques such as radiosity and global illumination, which tend to be very computationally intensive. In brief, model ing tends to be hard, and rendering is slow. For applications such as interior design, architectural planning, simulation, virtual museums and cultural heritage, the objects and environments that one wishes to render using the computer often exist within the real wor ld . In such cases, the model ing and rendering challenges increase considerably: since people are famil iar with what the results should look like, they will have higher expectations of the quality of the results. However, objects and environments in the real world have a very useful property as well: they can be photographed.Additionally, a great deal of research has been done in the last several years to model the geometry and appearance of objects and scenes from photographs. Computer vision concerns the development of algorithms to derive various sorts of information from digital images. The process of recover ing 3D structure f rom 2D photographs, now known as image-based modeling, has been one of its central endeavors. Conversely, the process of photorealistically rendering objects and scenes from images and geometry is known as image-based rendering. As the models come from photographs, modeling need not be hard, and since the shading also comes f rom the images, rendering need not be slow. In the next few sections, I'll discuss a number of image-based modeling techniques and some projects that have used them in conjunction with image-based rendering.
关于抑制约束误差的爱因斯坦方程离散格式
DOI：
--
发表时间：
2020
期刊：
影响因子：
--
作者：
石井 将大;照屋 唯紀;安田 貴徳;Sabrou Saitoh;H. Kawasaki;星野秀朋，佐藤慧，米田元
通讯作者：
星野秀朋，佐藤慧，米田元