Rotation Invariant Convolutions for 3D Point Clouds Deep Learning
By Zhiyuan Zhang, Binh-Son Hua, D. Rosen, Sai-Kit Yeung. 2019
199 citations recorded by the source corpus.
Recent progresses in 3D deep learning has shown that it is possible to design special convolution operators to consume point cloud data. However, a typical drawback is that rotation invariance is often not guaranteed, resulting in networks that generalizes poorly to arbitrary rotations. In this paper, we introduce a novel convolution operator for point clouds that achieves rotation invariance. Our core idea is to use low-level rotation invariant geometric features such as distances and angles to design a convolution operator for point cloud learning. The well-known point ordering problem is also addressed by a binning approach seamlessly built into the convolution. This convolution operator then serves as the basic building block of a neural network that is robust to point clouds under 6-DoF transformations such as translation and rotation. Our experiment shows that our method performs with high accuracy in common scene understanding tasks such as object classification and segmentation. Compared to previous and concurrent works, most importantly, our method is able to generalize and achieve consistent results across different scenarios in which training and testing can contain arbitrary rotations. Our implementation is publicly available at our project page.
Subfields: Aerospace Engineering, Computational Mechanics, Geology
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Aerospace Engineering
- Or Litany
- Andrea Tagliasacchi
- M. Ovsjanikov
- Adrien Poulenard
- Fabian B. Fuchs
- Souhaib Attaiki
- Keenan Crane
- Nicholas Sharp
In Computational Mechanics
- Or Litany
- M. Ovsjanikov
- Andrea Tagliasacchi
- Max Welling
- Adrien Poulenard
- Keenan Crane
- Souhaib Attaiki
- Nicholas Sharp
In Geology
- Or Litany
- Andrea Tagliasacchi
- M. Ovsjanikov
- Adrien Poulenard
- Souhaib Attaiki
- Keenan Crane
- Nicholas Sharp
- Fabian B. Fuchs
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].”
- DiffusionNet: Discretization Agnostic Learning on Surfaces (2020, background): “Moreover, recent efforts have also been made to incorporate invariance and equivariance of the networks with respect to various geometric transformations, e.g. , [Deng et al. 2018; Hansen et al. 2018; Li et al. 2021; Poulenard et al. 2019; Zhang et al. 2019; Zhao et al. 2020].”
- 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.”