|TREND||DATASET||BEST METHOD||PAPER TITLE||PAPER||CODE||COMPARE|
In this paper, we utilize the unique properties of the mesh for a direct analysis of 3D shapes using MeshCNN, a convolutional neural network designed specifically for triangular meshes.
The Adaptive O-CNN encoder takes the planar patch normal and displacement as input and performs 3D convolutions only at the octants at each level, while the Adaptive O-CNN decoder infers the shape occupancy and subdivision status of octants at each level and estimates the best plane normal and displacement for each leaf octant.
However, there is little effort on using mesh data in recent years, due to the complexity and irregularity of mesh data.
Convolutional neural networks (CNNs) have massively impacted visual recognition in 2D images, and are now ubiquitous in state-of-the-art approaches.
The bidirectional LSTM model with attention is found to be the best model in terms of accuracy (74. 1%) and f-score (74. 3%).
SOTA for 3D Shape Analysis on 2017_test set
However, persistence diagrams are multi-sets of points and hence it is not straightforward to fuse them with features used for contemporary machine learning tools like deep-nets.
Recently, there has been an increasing interest in geometric deep learning, attempting to generalize deep learning methods to non-Euclidean structured data such as graphs and manifolds, with a variety of applications from the domains of network analysis, computational social science, or computer graphics.
#4 best model for Document Classification on Cora