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

Francis Williams
Francis Williams
Matthew Trager
Matthew Trager
Cited by: 0|Bibtex|Views24|Links

Abstract:

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 Screened Poisson Surface Reconstruction and modern neural network based techniques. Because our approach is based on ...More

Code:

Data:

Your rating :
0

 

Tags
Comments