22/11/2021

Two Heads are Better than One: Geometric-Latent Attention for Point Cloud Classification and Segmentation

Hanz Cuevas, Antonio-Javier Gallego, Robert B Fisher

Keywords: point cloud, point cloud segmentation, 3D, point cloud classification, shape classification, deep 3D segmentation, deep learning, scene understanding, 3D scene understanding, light network, local agregation, gnn

Abstract: We present an innovative two-headed attention layer that combines geometric and latent features to segment a 3D scene into semantically meaningful subsets. Each head combines local and global information, using either the geometric or latent features, of a neighborhood of points and uses this information to learn better local relationships. This Geometric-Latent attention layer (Ge-Latto) is combined with a sub-sampling strategy to capture global features. Our method is invariant to permutation thanks to the use of shared-MLP layers, and it can also be used with point clouds with varying densities because the local attention layer does not depend on the neighbor order. Our proposal is simple yet robust, which allows it to achieve competitive results in the ShapeNetPart and ModelNet40 datasets, and the state-of-the-art when segmenting the complex dataset S3DIS, with 69.2% IoU on Area 5, and 89.7% overall accuracy using K-fold cross-validation on the 6 areas.

 0
 0
 0
 0
This is an embedded video. Talk and the respective paper are published at BMVC 2021 virtual conference. If you are one of the authors of the paper and want to manage your upload, see the question "My papertalk has been externally embedded..." in the FAQ section.

Comments

Post Comment
no comments yet
code of conduct: tbd Characters remaining: 140

Similar Papers