Differentiable Surface Rendering via Non-Differentiable Sampling
Differentiable Surface Rendering via Non-Differentiable Sampling
复制标题
通过不可微采样进行可微表面渲染
DOI：
--
复制
发表时间：
2021
期刊：
影响因子：
--
通讯作者：
Zhoutong Zhang
中科院分区：
文献类型：
--
作者：
Forrester Cole;Kyle Genova;Avneesh Sud;Daniel Vlasic;Zhoutong Zhang
我们提出了一种方法，可微分渲染的3D表面，支持显式和隐式表示，提供衍生物在遮挡边界，是快速和简单的实现。该方法首先使用不可微光栅化对表面进行采样，然后应用可微的、深度感知的点溅射来产生最终图像。我们的方法不需要可微的网格化或光栅化步骤，使其有效的大型3D模型和适用于从隐式表面定义提取的等值面。我们证明了我们的方法的有效性隐式，网格和参数化表面为基础的逆绘制和神经网络训练应用程序。特别是，我们首次展示了从神经辐射场（NeRF）中提取的等值面的高效，可微分渲染，并展示了基于表面而不是基于体积的NeRF渲染。
We present a method for differentiable rendering of 3D surfaces that supports both explicit and implicit representations, provides derivatives at occlusion boundaries, and is fast and simple to implement. The method first samples the surface using non-differentiable rasterization, then applies differentiable, depth-aware point splatting to produce the final image. Our approach requires no differentiable meshing or rasterization steps, making it efficient for large 3D models and applicable to isosurfaces extracted from implicit surface definitions. We demonstrate the effectiveness of our method for implicit-, mesh-, and parametric-surface-based inverse rendering and neural-network training applications. In particular, we show for the first time efficient, differentiable rendering of an isosurface extracted from a neural radiance field (NeRF), and demonstrate surface-based, rather than volume-based, rendering of a NeRF.