论文标题
阴影处理的神经反射率用于形状恢复
Neural Reflectance for Shape Recovery with Shadow Handling
论文作者
论文摘要
本文旨在用未知，非陆层和可能在空间上变化的表面材料恢复场景的形状。当对象的形状高度复杂并且阴影在表面上时，任务就变得非常具有挑战性。为了克服这些挑战，我们提出了一个基于坐标的深MLP（多层感知器），以参数化未知的3D形状和在每个表面上的未知反射率。该网络能够利用观察到的光度方差和表面的阴影，并恢复表面形状和一般非lambertian反射率。我们明确预测铸造阴影，减轻这些阴影区域上可能的伪像，从而提高估计精度。从某种意义上说，我们的框架完全不需要地面真理，也不需要BRDF。对现实世界图像的测试表明，我们的方法的表现优于现有方法的大幅度余量。由于MLP-NET的尺寸较小，我们的方法比以前基于CNN的方法快的数量级。
This paper aims at recovering the shape of a scene with unknown, non-Lambertian, and possibly spatially-varying surface materials. When the shape of the object is highly complex and that shadows cast on the surface, the task becomes very challenging. To overcome these challenges, we propose a coordinate-based deep MLP (multilayer perceptron) to parameterize both the unknown 3D shape and the unknown reflectance at every surface point. This network is able to leverage the observed photometric variance and shadows on the surface, and recover both surface shape and general non-Lambertian reflectance. We explicitly predict cast shadows, mitigating possible artifacts on these shadowing regions, leading to higher estimation accuracy. Our framework is entirely self-supervised, in the sense that it requires neither ground truth shape nor BRDF. Tests on real-world images demonstrate that our method outperform existing methods by a significant margin. Thanks to the small size of the MLP-net, our method is an order of magnitude faster than previous CNN-based methods.
