Spherical Fractal Convolutional Neural Networks for Point Cloud Recognition

By Yongming Rao, Jiwen Lu, Jie Zhou. 2019

170 citations recorded by the source corpus.

We present a generic, flexible and 3D rotation invariant framework based on spherical symmetry for point cloud recognition. By introducing regular icosahedral lattice and its fractals to approximate and discretize sphere, convolution can be easily implemented to process 3D points. Based on the fractal structure, a hierarchical feature learning framework together with an adaptive sphere projection module is proposed to learn deep feature in an end-to-end manner. Our framework not only inherits the strong representation power and generalization capability from convolutional neural networks for image recognition, but also extends CNN to learn robust feature resistant to rotations and perturbations. The proposed model is effective yet robust. Comprehensive experimental study demonstrates that our approach can achieve competitive performance compared to state-of-the-art techniques on both 3D object classification and part segmentation tasks, meanwhile, outperform other rotation invariant models on rotated 3D object classification and retrieval tasks by a large margin.

Subfields: Computational Mechanics, Computer Vision and Pattern Recognition, 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

In Computer Vision and Pattern Recognition

In Geology

Citations in the corpus

SE(3)-Transformers: 3D Roto-Translation Equivariant Attention Networks (2020, methodology): “Our method sets itself apart by using roto-translation equivariant layers acting directly on the point cloud without prior projection onto a sphere [22, 45, 7].”
SphereFace Revived: Unifying Hyperspherical Face Recognition (2021, background): “Beyond face recognition, the idea of learning a representation on the hypersphere is also shown generally useful in a diverse set of applications, such as few-shot recognition [47], [48], [49], [50], [51], deep metric learning [25], [52], self-supervised learning [53], [54], [55], [56], generative m”
SpinNet: Learning a General Surface Descriptor for 3D Point Cloud Registration (2020, background): “Accurate matching of partial 3D surfaces is critical for point cloud registration [17, 38, 6, 21, 29], segmentation [58, 28, 27], and recognition [24, 12, 47].”
Deep Learning for 3D Point Clouds: A Survey (2019, background): “SFCNN is resistant to rotations and perturbations.”
Review: deep learning on 3D point clouds (2020, methodology): “SFCNN [24] uses a a fractalized regular icosahedral lattice to map points onto a discretized sphere and defined a multi-scale convolution operation on the regular shperical lattice.”
Vector Neurons: A General Framework for SO(3)-Equivariant Networks (2021, methodology): “SFCNN [27] proposes an approach similar to multi-view by mapping input pointclouds to a sphere and performing operations on the sphere.”
Rotation Invariant Convolutions for 3D Point Clouds Deep Learning (2019, background): “A few convolution operators that allows rotation invariance exist [8, 27] but consistent predictions with arbitrarily rotated data are still not achieved.”