Rotation invariance and equivariance in 3D deep learning: a survey
J Fei, Z Deng - Artificial Intelligence Review, 2024 - Springer
Deep neural networks (DNNs) in 3D scenes show a strong capability of extracting high-level
semantic features and significantly promote research in the 3D field. 3D shapes and scenes …
semantic features and significantly promote research in the 3D field. 3D shapes and scenes …
MaskLRF: Self-supervised Pretraining via Masked Autoencoding of Local Reference Frames for Rotation-invariant 3D Point Set Analysis
T Furuya - IEEE Access, 2024 - ieeexplore.ieee.org
Following the successes in the fields of vision and language, self-supervised pretraining via
masked autoencoding of 3D point set data, or Masked Point Modeling (MPM), has achieved …
masked autoencoding of 3D point set data, or Masked Point Modeling (MPM), has achieved …
Enhancing Robustness to Noise Corruption for Point Cloud Model via Spatial Sorting and Set-Mixing Aggregation Module
Current models for point cloud recognition demonstrate promising performance on synthetic
datasets. However, real-world point cloud data inevitably contains noise, impacting model …
datasets. However, real-world point cloud data inevitably contains noise, impacting model …