We present Neural Splines, a technique for 3D surface reconstruction that is based on random feature kernels arising from infinitely-wide shallow ReLU networks. Our method achieves state-of-the-art results, outperforming recent neural network-based techniques and widely used Poisson Surface Reconstruction (which, as we demonstrate, can also be viewed as a type of kernel method). Because our approach is based on a simple kernel formulation, it is easy to analyze and can be accelerated by general techniques designed for kernel-based learning. We provide explicit analytical expressions for our kernel and argue that our formulation can be seen as a generalization of cubic spline interpolation to higher dimensions. In particular, the RKHS norm associated with Neural Splines biases toward smooth interpolants.
翻译:我们展示了3D地表重建技术,即3D地表重建技术,它基于无穷无尽的浅射线网络产生的随机特质内核。我们的方法取得了最新的结果,优于最近的神经网络技术和广泛使用的Poisson地表重建技术(正如我们所显示的那样,这也可以被视为一种内核方法 ) 。由于我们的方法基于简单的内核配方,因此很容易分析,并且可以通过为内核学习设计的一般技术加速。我们为我们内核提供了明确的分析表达方式,并论证我们的配方可以被视为将立体螺旋内插到更高层面的普遍化。特别是,与神经线偏向光滑的内流相关的RKHS规范。