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 …
AS Gezawa, Y Zhang, Q Wang, L Yunqi - IEEE access, 2020 - ieeexplore.ieee.org
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 …
X He, Y Zhou, Z Zhou, S Bai… - Proceedings of the IEEE …, 2018 - openaccess.thecvf.com
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 …
R Kondor, Z Lin, S Trivedi - Advances in Neural Information …, 2018 - proceedings.neurips.cc
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 …
X Chen, K Jiang, Y Zhu, X Wang, T Yun - Forests, 2021 - mdpi.com
Accurate individual tree crown (ITC) segmentation from scanned point clouds is a fundamental task in forest biomass monitoring and forest ecology management. Light …
Y Rao, J Lu, J Zhou - … of the IEEE/CVF conference on …, 2019 - openaccess.thecvf.com
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 …