Deep Point Cloud Normal Estimation via Triplet Learning

by   Weijia Wang, et al.

Normal estimation on 3D point clouds is a fundamental problem in 3D vision and graphics. Current methods often show limited accuracy in predicting normals at sharp features (e.g., edges and corners) and less robustness to noise. In this paper, we propose a novel normal estimation method for point clouds. It consists of two phases: (a) feature encoding which learns representations of local patches, and (b) normal estimation that takes the learned representation as input and regresses the normal vector. We are motivated that local patches on isotropic and anisotropic surfaces have similar or distinct normals, and that separable features or representations can be learned to facilitate normal estimation. To realise this, we first construct triplets of local patches on 3D point cloud data, and design a triplet network with a triplet loss for feature encoding. We then design a simple network with several MLPs and a loss function to regress the normal vector. Despite having a smaller network size compared to most other methods, experimental results show that our method preserves sharp features and achieves better normal estimation results on CAD-like shapes.


page 5

page 6

page 7

page 11

page 12

page 13


Contrastive Learning for Joint Normal Estimation and Point Cloud Filtering

Point cloud filtering and normal estimation are two fundamental research...

Weighted Point Cloud Normal Estimation

Existing normal estimation methods for point clouds are often less robus...

Point cloud ridge-valley feature enhancement based on position and normal guidance

Ridge-valley features are important elements of point clouds, as they co...

NeAF: Learning Neural Angle Fields for Point Normal Estimation

Normal estimation for unstructured point clouds is an important task in ...

SHS-Net: Learning Signed Hyper Surfaces for Oriented Normal Estimation of Point Clouds

We propose a novel method called SHS-Net for oriented normal estimation ...

GraphFit: Learning Multi-scale Graph-Convolutional Representation for Point Cloud Normal Estimation

We propose a precise and efficient normal estimation method that can dea...

Learning Geometry-Disentangled Representation for Complementary Understanding of 3D Object Point Cloud

In 2D image processing, some attempts decompose images into high and low...

Please sign up or login with your details

Forgot password? Click here to reset