ClusterNet: Deep Hierarchical Cluster Network With Rigorously Rotation-Invariant Representation for Point Cloud Analysis

By Chao Chen, Guanbin Li, Ruijia Xu, Tianshui Chen, Mei Wang, Liang Lin. 2019

189 citations recorded by the source corpus.

Current neural networks for 3D object recognition are vulnerable to 3D rotation. Existing works mostly rely on massive amounts of rotation-augmented data to alleviate the problem, which lacks solid guarantee of the 3D rotation invariance. In this paper, we address the issue by introducing a novel point cloud representation that can be mathematically proved rigorously rotation-invariant, i.e., identical point clouds in different orientations are unified as a unique and consistent representation. Moreover, the proposed representation is conditional information-lossless, because it retains all necessary information of point cloud except for orientation information. In addition, the proposed representation is complementary with existing network architectures for point cloud and fundamentally improves their robustness against rotation transformation. Finally, we propose a deep hierarchical cluster network called ClusterNet to better adapt to the proposed representation. We employ hierarchical clustering to explore and exploit the geometric structure of point cloud, which is embedded in a hierarchical structure tree. Extensive experimental results have shown that our proposed method greatly outperforms the state-of-the-arts in rotation robustness on rotation-augmented 3D object classification benchmarks.

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, background): “Some recent works explore rotation invariant point cloud classification [45, 47, 4, 22].”
Canonical Capsules: Unsupervised Capsules in Canonical Pose (2020, methodology): “We compare against three baselines: 1 Deep Closest Points [56], a deep learning-based pairwise point cloud registration method; 2 DeepGMR [63] a state-of-the-art pairwise registration method that decomposes clouds into Gaussian mixtures and utilizes Rigorously Rotation-Invariant (RRI) features [4]; ”
SpinNet: Learning a General Surface Descriptor for 3D Point Cloud Registration (2020, background): “In contrast to traditional handcrafted descriptors, recent works [10, 68, 3, 15, 63, 61] leverage data-driven deep neural networks to learn local features from large-scale datasets.”
RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Clouds (2019, background): “These modules can be generally categorized as: 1) neighbouring feature pooling [44, 32, 21, 70, 69], 2) graph message passing [57, 48, 55, 56, 5, 22, 34], 3) kernel-based convolution [49, 20, 60, 29, 23, 24, 54, 38], and 4) attentionbased aggregation [61, 68, 66, 42].”
Vector Neurons: A General Framework for SO(3)-Equivariant Networks (2021, background): “Many rotation invariant architectures [21, 24, 6, 39, 41, 18, 42, 27] have been proposed to address these issues.”
Deep Learning for 3D Point Clouds: A Survey (2019, methodology): “ClusterNet [95] utilizes a rigorously rotation-invariant module to extract rotation-invariant features from k nearest”