Papers › Neural Splines: Fitting 3D Surfaces with Infinitely-Wide Neural Networks

Neural Splines: Fitting 3D Surfaces with Infinitely-Wide Neural Networks

24 Jun 2020CVPR 2021 1arXiv:2006.13782archive 2025-07-28

Francis Williams, Matthew Trager, Joan Bruna, Denis Zorin

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.

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

fwilliams/neural-splines officialmentioned in papermentioned on GitHubpytorchMIT report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Surface Reconstruction

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

ReLU

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections