Neural Splines:用无限宽的神经网络拟合3D曲面
Neural Splines: Fitting 3D Surfaces with Infinitely-Wide Neural Networks
摘要:
我们提出了神经样条,这是一种用于3D表面重建的技术,它基于从无限宽的浅层ReLU网络中产生的随机特征内核。我们的方法达到了最先进的结果,优于最近的神经网络为基础的技术和广泛使用的泊松表面重建(这,正如我们所证明的,也可以被视为一种类型的内核方法)。因为我们的方法是基于一个简单的内核公式,它很容易分析,并可以加速基于内核的学习设计的一般技术。我们提供了明确的解析表达式,我们的内核,并认为我们的配方可以被看作是一个推广的三次样条插值到更高的维度。特别是,与神经样条相关的RKHS范数偏向于平滑插值。
英文摘要:
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.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。