The NeAF is designed to estimate normals for point clouds by learning implicit angle fields. Given a query vector sampled on the unit sphere and a local patch as input, the network outputs the angle offset between the query vector and the ground truth normal of the patch.
Nov 30, 2022 · We propose an implicit function to learn an angle field around the normal of each point in the spherical coordinate system, which is dubbed as Neural Angle ...
We propose Neural Angle Field (NeAF) for point normal estimation. Unlike previous methods, our implicit func- tion learns an angle field for each point, which ...
Instead of directly predicting the normal of an input point, we predict the angle offset between the ground truth normal and a randomly sampled query normal.
To predict normals from the learned angle fields at inference time, we randomly sample query vectors in a unit spherical space and take the vectors with minimal ...
NeAF: Learning Neural Angle Fields for Point Normal Estimation (AAAI 2023 oral) Shujuan Li* · Junsheng Zhou* · Baorui Ma · Yu-Shen Liu · Zhizhong Han
NeAF: Learning Neural Angle Fields for Point Normal Estimation · 1 code implementation • 30 Nov 2022 • Shujuan Li, Junsheng Zhou, Baorui Ma, Yu-Shen Liu ...
Neaf: Learning neural angle fields for point normal estimation · Learning a more continuous zero level set in unsigned distance fields through level set ...
Dec 12, 2023 · We propose Neural Gradient Learning (NGL), a deep learning approach to learn gradient vectors with consistent orientation from 3D point clouds for normal ...
This work proposes a novel method for estimating oriented normals directly from point clouds without using ground truth normals as supervision.