arXiv (Cornell University) · 2020 · 22 citations · 23 references
ComputingComputer ScienceComputational GeometryComputer VisionMachine LearningCoordinate TransformationsDeep LearningNeural NetworksPattern RecognitionPoint Cloud ProcessingShape RepresentationPoint Cloud RepresentationPoint Cloud Representation Learning
Learning functions on point clouds has applications in many fields, including computer vision, computer graphics, physics, and chemistry. Recently, there has been a growing interest in neural architectures that are invariant or equivariant to all three shape-preserving transformations of point clouds: translation, rotation, and permutation. In this paper, we present a first study of the approximation power of these architectures. We first derive two sufficient conditions for an equivariant architecture to have the universal approximation property, based on a novel characterization of the space of equivariant polynomials. We then use these conditions to show that two recently suggested models are universal, and for devising two other novel universal architectures.
23
PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
Raffaelli Charles, Hao Su, Kaichun Mo et al. · 2017 · 9.8K citations
Dynamic Graph CNN for Learning on Point Clouds
Yue Wang, Yongbin Sun, Ziwei Liu et al. · ACM Transactions on Graphics · 2019 · 6.7K citations · Full text
Deep Learning for 3D Point Clouds: A Survey
Yulan Guo, Hanyun Wang, Qingyong Hu et al. · IEEE Transactions on Pattern Analysis and Machine Intelligence · 2020 · 2.3K citations
Neural Message Passing for Quantum Chemistry
Justin Gilmer, Samuel S. Schoenholz, Patrick Riley et al. · arXiv (Cornell University) · 2017 · 1.2K citations · Full text