Vectorization for Fast, Analytic, and Differentiable Visibility
Vectorization for Fast, Analytic, and Differentiable Visibility
复制标题
用于快速、分析和可微分可见性的矢量化
作者：
Yang Zhou;Lifan Wu;R. Ramamoorthi;Ling
在计算机图形学中，渲染和可见性的两种主要方法涉及光线跟踪和光栅化。然而，这两种方法的局限性在于它们基本上使用点采样。这是噪声和混叠的来源，并且还导致可区分渲染的显著困难。在这项工作中，我们提出了一种新的渲染方法，我们称之为矢量化，计算2D点到区域积分解析，从而消除点采样在2D积分域，如像素足迹和区域灯。我们的矢量化重新访问的概念，光束跟踪，并处理隐藏的表面去除问题的鲁棒性和准确性。也就是说，对于以任意顺序插入到梁视口中的每个相交三角形，我们能够保持由相交和遮挡形成的所有可见区域，这要归功于我们的可见性边界体层次结构。因此，我们的矢量化可以产生完美的抗锯齿可见性，准确和分析的着色和阴影，最重要的是，快速和无噪声的梯度与自动微分或有限差分，直接实现可微分渲染，而无需对我们的渲染管道进行任何更改。我们的结果本质上是高质量和无噪声的，我们的梯度是一个到两个数量级的速度比现有的微分渲染方法计算。
In Computer Graphics, the two main approaches to rendering and visibility involve ray tracing and rasterization. However, a limitation of both approaches is that they essentially use point sampling. This is the source of noise and aliasing, and also leads to significant difficulties for differentiable rendering. In this work, we present a new rendering method, which we call vectorization, that computes 2D point-to-region integrals analytically, thus eliminating point sampling in the 2D integration domain such as for pixel footprints and area lights. Our vectorization revisits the concept of beam tracing, and handles the hidden surface removal problem robustly and accurately. That is, for each intersecting triangle inserted into the viewport of a beam in an arbitrary order, we are able to maintain all the visible regions formed by intersections and occlusions, thanks to our Visibility Bounding Volume Hierarchy structure. As a result, our vectorization produces perfectly anti-aliased visibility, accurate and analytic shading and shadows, and most important, fast and noise-free gradients with Automatic Differentiation or Finite Differences that directly enables differentiable rendering without any changes to our rendering pipeline. Our results are inherently high-quality and noise-free, and our gradients are one to two orders of magnitude faster than those computed with existing differentiable rendering methods.
DOI：
10.1145/3306346.3322936
发表时间：
2019-07
期刊：
ACM Transactions on Graphics (TOG)
影响因子：
--
作者：
Lifan Wu;Shuang Zhao;Ling-Qi Yan;R. Ramamoorthi
通讯作者：
Lifan Wu;Shuang Zhao;Ling-Qi Yan;R. Ramamoorthi
影响因子：
3.6
作者：
Kar, Subrata;Talukdar, Sarmistha;Kundu, S. C.
通讯作者：
Kundu, S. C.