3D-Rotation-Equivariant Quaternion Neural Networks
This paper proposes a set of rules to revise various neural networks for 3D point cloud processing to rotation-equivariant quaternion neural networks (REQNNs). We find that when a neural network uses quaternion features under certain conditions, the network feature naturally has the rotation-equivariance property. Rotation equivariance means that applying a specific rotation transformation to the input point cloud is equivalent to applying the same rotation transformation to all intermediate-layer quaternion features. Besides, the REQNN also ensures that the intermediate-layer features are invariant to the permutation of input points. Compared with the original neural network, the REQNN exhibits higher rotation robustness.
Code (1)
Similar Papers 제목 키워드 기반
Quaternion Product Units for Deep Learning on 3D Rotation Groups
We propose a novel quaternion product unit (QPU) to represent data on 3D rotation groups. The QPU leverages quaternion algebra and the law of 3D rotation group, representing 3D rotation data as quaternions and merging th…
Deep LearningDual Quaternion Rotational and Translational Equivariance in 3D Rigid Motion Modelling
Objects' rigid motions in 3D space are described by rotations and translations of a highly-correlated set of points, each with associated $x,y,z$ coordinates that real-valued networks consider as separate entities, losin…
Human Pose ForecastingQuaternion Approximation Networks for Enhanced Image Classification and Oriented Object Detection
This paper introduces Quaternion Approximate Networks (QUAN), a novel deep learning framework that leverages quaternion algebra for rotation equivariant image classification and object detection. Unlike conventional quat…
Image ClassificationObject DetectionQuaternion Equivariant Capsule Networks for 3D Point Clouds
We present a 3D capsule module for processing point clouds that is equivariant to 3D rotations and translations, as well as invariant to permutations of the input points. The operator receives a sparse set of local refer…
Pose EstimationRotation-Invariant Gait Identification with Quaternion Convolutional Neural Networks
A desireable property of accelerometric gait-based identification systems is robustness to new device orientations presented by users during testing but unseen during the training phase. However, traditional Convolutiona…
Gait Identification