Convolutional Neural Networks (CNNs) have become the method of choice for learning
problems involving 2D planar images. However, a number of problems of recent interest …

We present a convolutional network that is equivariant to rigid body motions. The model
uses scalar-, vector-, and tensor fields over 3D Euclidean space to represent data, and …

We address the problem of 3D rotation equivariance in convolutional neural networks. 3D
rotations have been a challenging nuisance in 3D classification tasks requiring higher …

Deep learning approach has been used extensively in image analysis tasks. However,
implementing the methods in 3D data is a bit complex because most of the previously …

Most existing 3D object recognition algorithms focus on leveraging the strong discriminative
power of deep learning models with softmax loss for the classification of 3D data, while …

Recent work by Cohen et al. has achieved state-of-the-art results for learning spherical
images in a rotation invariant way by using ideas from group representation theory and …

Accurate individual tree crown (ITC) segmentation from scanned point clouds is a
fundamental task in forest biomass monitoring and forest ecology management. Light …

We present a generic, flexible and 3D rotation invariant framework based on spherical
symmetry for point cloud recognition. By introducing regular icosahedral lattice and its …

Recently, many deep neural networks were designed to process 3D point clouds, but a
common drawback is that rotation invariance is not ensured, leading to poor generalization …

Several popular approaches to 3D vision tasks process multiple views of the input
independently with deep neural networks pre-trained on natural images, where view …