Classify 3D Point Clouds
4 papers with code • 0 benchmarks • 2 datasets
Benchmarks
These leaderboards are used to track progress in Classify 3D Point Clouds
ModelNet40-C
RobustPointSet
Most implemented papers
Flex-Convolution (Million-Scale Point-Cloud Learning Beyond Grid-Worlds)
cgtuebingen/Flex-Convolution
•
•
Traditional convolution layers are specifically designed to exploit the natural data representation of images -- a fixed and regular grid.
Point Convolutional Neural Networks by Extension Operators
matanatz/pcnn
•
•
This paper presents Point Convolutional Neural Networks (PCNN): a novel framework for applying convolutional neural networks to point clouds.
AdvPC: Transferable Adversarial Perturbations on 3D Point Clouds
Our proposed attack increases the attack success rate by up to 40% for those transferred to unseen networks (transferability), while maintaining a high success rate on the attacked network.
Geometric Algebra Attention Networks for Small Point Clouds
klarh/flowws-keras-geometry
•
•
Much of the success of deep learning is drawn from building architectures that properly respect underlying symmetry and structure in the data on which they operate - a set of considerations that have been united under the banner of geometric deep learning.
