Deep Learning for Robust Normal Estimation in Unstructured Point Clouds

By Alexandre Boulch, Renaud Marlet. 2016

164 citations recorded by the source corpus.

Subfields: Computational Mechanics, Computer Graphics and Computer-Aided Design, Geology

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computational Mechanics

1. Daniel Cohen-Or
2. M. Ovsjanikov
3. P. Heng
4. Chi-Wing Fu
5. Niloy J. Mitra
6. Olga Sorkine-Hornung
7. Paul Guerrero
8. Lequan Yu

In Computer Graphics and Computer-Aided Design

1. Daniel Cohen-Or
2. M. Ovsjanikov
3. P. Heng
4. Chi-Wing Fu
5. Niloy J. Mitra
6. Olga Sorkine-Hornung
7. Marc Alexa
8. Lequan Yu

In Geology

1. Daniel Cohen-Or
2. P. Heng
3. Chi-Wing Fu
4. Bertrand Le Saux
5. Nicolas Audebert
6. Joris Guerry
7. Niloy J. Mitra
8. M. Ovsjanikov

Citations in the corpus

• PCPNet Learning Local Shape Properties from Raw Point Clouds (2017, methodology): “For Boulch et al. [BM16], we use the single-scale, 3-scale and 5-scale networks provided by the authors.”
• EC-Net: an Edge-aware Point set Consolidation Network (2018, background): “To do so, early works extracted low-level geometric features as inputs to CNNs [22,23].”
• ABC: A Big CAD Model Dataset for Geometric Deep Learning (2018, background): “It would be interesting to run a similar study by extending these algorithms to correctly identify and predict multiple normals on sharp features and compare them with specialized methods for this task [17].”
• SnapNet: 3D point cloud semantic labeling with 2D deep segmentation networks (2017, methodology): “It requires as inut a point-cloud with normals, which we estimate by using the vailable code from [34] .”
• Unstructured Point Cloud Semantic Labeling Using Deep Segmentation Networks (2017, methodology): “It requires as input a point-cloud with normals, which we estimate by us-ing the available code from [BM16].”