paper-with-me

홈 › Papers

3D-Rotation-Equivariant Quaternion Neural Networks

2019-11-20 · ECCV 2020 8 · Wen Shen, BinBin Zhang, Shikun Huang, Zhihua Wei, Quanshi Zhang

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.

📄 PDF Abstract BibTeX arXiv:1911.09040

Code (1)

ada-shen/REQNN pytorch

Similar Papers 제목 키워드 기반

Quaternion Product Units for Deep Learning on 3D Rotation Groups

2019-12-17 · CVPR 2020 6 · Xuan Zhang, Shaofei Qin, Yi Xu, Hongteng Xu

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 Learning

Dual Quaternion Rotational and Translational Equivariance in 3D Rigid Motion Modelling

2023-10-11 · Guilherme Vieira, Eleonora Grassucci, Marcos Eduardo Valle, Danilo Comminiello

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 Forecasting

Quaternion Approximation Networks for Enhanced Image Classification and Oriented Object Detection

2025-09-05 · Bryce Grant, Peng Wang arxiv

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 Detection

Quaternion Equivariant Capsule Networks for 3D Point Clouds

2019-12-27 · ECCV 2020 8 · Yongheng Zhao, Tolga Birdal, Jan Eric Lenssen, Emanuele Menegatti 외

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 Estimation

Rotation-Invariant Gait Identification with Quaternion Convolutional Neural Networks

2020-08-04 · Bowen Jing, Vinay Prabhu, Angela Gu, John Whaley

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