# Nesti-Net: Normal Estimation for Unstructured 3D Point Clouds using Convolutional Neural Networks

## TL;DR

Nesti-Net introduces a CNN-based method for estimating normals in unstructured 3D point clouds, utilizing a multi-scale local representation and a mixture-of-experts architecture to improve robustness and accuracy.

## Contribution

The paper presents a novel local point cloud representation (MuPS) and a mixture-of-experts CNN architecture for normal estimation, enhancing robustness to noise and density variations.

## Key findings

- Achieves state-of-the-art results on synthetic datasets.
- Improves robustness to noise and point density variations.
- Provides qualitative results on real scanned scenes.

## Abstract

In this paper, we propose a normal estimation method for unstructured 3D point clouds. This method, called Nesti-Net, builds on a new local point cloud representation which consists of multi-scale point statistics (MuPS), estimated on a local coarse Gaussian grid. This representation is a suitable input to a CNN architecture. The normals are estimated using a mixture-of-experts (MoE) architecture, which relies on a data-driven approach for selecting the optimal scale around each point and encourages sub-network specialization. Interesting insights into the network's resource distribution are provided. The scale prediction significantly improves robustness to different noise levels, point density variations and different levels of detail. We achieve state-of-the-art results on a benchmark synthetic dataset and present qualitative results on real scanned scenes.