TY - JOUR
T1 - Orienting point clouds with dipole propagation
AU - Metzer, Gal
AU - Hanocka, Rana
AU - Zorin, Denis
AU - Giryes, Raja
AU - Panozzo, Daniele
AU - Cohen-Or, Daniel
N1 - Publisher Copyright:
© 2021 ACM.
PY - 2021/7/1
Y1 - 2021/7/1
N2 - Establishing a consistent normal orientation for point clouds is a notoriously difficult problem in geometry processing, requiring attention to both local and global shape characteristics. The normal direction of a point is a function of the local surface neighborhood; yet, point clouds do not disclose the full underlying surface structure. Even assuming known geodesic proximity, calculating a consistent normal orientation requires the global context. In this work, we introduce a novel approach for establishing a globally consistent normal orientation for point clouds. Our solution separates the local and global components into two different sub-problems. In the local phase, we train a neural network to learn a coherent normal direction per patch (i.e., consistently oriented normals within a single patch). In the global phase, we propagate the orientation across all coherent patches using a dipole propagation. Our dipole propagation decides to orient each patch using the electric field defined by all previously orientated patches. This gives rise to a global propagation that is stable, as well as being robust to nearby surfaces, holes, sharp features and noise.
AB - Establishing a consistent normal orientation for point clouds is a notoriously difficult problem in geometry processing, requiring attention to both local and global shape characteristics. The normal direction of a point is a function of the local surface neighborhood; yet, point clouds do not disclose the full underlying surface structure. Even assuming known geodesic proximity, calculating a consistent normal orientation requires the global context. In this work, we introduce a novel approach for establishing a globally consistent normal orientation for point clouds. Our solution separates the local and global components into two different sub-problems. In the local phase, we train a neural network to learn a coherent normal direction per patch (i.e., consistently oriented normals within a single patch). In the global phase, we propagate the orientation across all coherent patches using a dipole propagation. Our dipole propagation decides to orient each patch using the electric field defined by all previously orientated patches. This gives rise to a global propagation that is stable, as well as being robust to nearby surfaces, holes, sharp features and noise.
KW - geometric deep learning
KW - point clouds
KW - surface reconstruction
UR - http://www.scopus.com/inward/record.url?scp=85108507749&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85108507749&partnerID=8YFLogxK
U2 - 10.1145/3450626.3459835
DO - 10.1145/3450626.3459835
M3 - Article
AN - SCOPUS:85108507749
SN - 0730-0301
VL - 40
JO - ACM Transactions on Graphics
JF - ACM Transactions on Graphics
IS - 4
M1 - 165
ER -