Representation learning on unit ball with 3D roto-translational equivariance

DOI10.1007/s11263-019-01278-xzbMath1471.68284arXiv1912.01454OpenAlexW2995563631WikidataQ126523733 ScholiaQ126523733MaRDI QIDQ2226187

Yanyan Li

Publication date: 11 February 2021

Published in: International Journal of Computer Vision (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1912.01454

zbMATH Keywords

Zernike polynomialsconvolutional neural networksdeep learning3D momentsvolumetric convolution

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Computer graphics; computational geometry (digital and algorithmic aspects) (68U05) Machine vision and scene understanding (68T45)

Uses Software

• ImageNet
• PointNet
• SPLATNet
• VoxNet
• AlexNet

Cites Work

• Unnamed Item
• Chebyshev-type methods and preconditioning techniques
• Efficient 3D shape matching and retrieval using a concrete radialized spherical projection representation
• Design and processing of invertible orientation scores of 3D images
• The ``cubed sphere: A new method for the solution of partial differential equations in spherical geometry
• Shape distributions
• Computer Vision - ECCV 2004

This page was built for publication: Representation learning on unit ball with 3D roto-translational equivariance