Neural radiosity
Neural radiosity
复制标题
DOI：
10.1145/3478513.3480569
复制
发表时间：
2021-05
期刊：
影响因子：
--
通讯作者：
Saeed Hadadan;Shuhong Chen;Matthias Zwicker
中科院分区：
文献类型：
--
作者：
Saeed Hadadan;Shuhong Chen;Matthias Zwicker
我们介绍神经辐射度，一种算法来解决渲染方程，通过最小化其残差的范数，类似于在经典的辐射度技术。在辐射度中使用的传统基函数，例如分段多项式或无网格基函数，通常限于表示来自漫射表面的各向同性散射。相反，我们建议利用神经网络来表示完整的四维辐射分布，直接优化网络参数以最小化残差的范数。我们的方法从渲染（透视）图像类似于在传统的辐射度技术，并允许我们有效地合成场景的任意视图，解决渲染方程。此外，我们提出了一个网络架构，使用几何可学习的功能，提高我们的求解器的收敛性相比，以前的技术。我们的方法导致一个算法，是简单的实现，我们证明了它的有效性在各种场景的漫反射和非漫反射表面。
We introduce Neural Radiosity, an algorithm to solve the rendering equation by minimizing the norm of its residual, similar as in classical radiosity techniques. Traditional basis functions used in radiosity, such as piecewise polynomials or meshless basis functions are typically limited to representing isotropic scattering from diffuse surfaces. Instead, we propose to leverage neural networks to represent the full four-dimensional radiance distribution, directly optimizing network parameters to minimize the norm of the residual. Our approach decouples solving the rendering equation from rendering (perspective) images similar as in traditional radiosity techniques, and allows us to efficiently synthesize arbitrary views of a scene. In addition, we propose a network architecture using geometric learnable features that improves convergence of our solver compared to previous techniques. Our approach leads to an algorithm that is simple to implement, and we demonstrate its effectiveness on a variety of scenes with diffuse and non-diffuse surfaces.