Sparse 3D convolutional neural networks

Add code
Aug 25, 2015
Ben Graham
Figure 1 for Sparse 3D convolutional neural networks
Figure 2 for Sparse 3D convolutional neural networks
Figure 3 for Sparse 3D convolutional neural networks
Figure 4 for Sparse 3D convolutional neural networks

Share this with someone who'll enjoy it:

Twitter IconFacebook IconLinkedin IconWhatsapp IconMessenger Icon

We have implemented a convolutional neural network designed for processing sparse three-dimensional input data. The world we live in is three dimensional so there are a large number of potential applications including 3D object recognition and analysis of space-time objects. In the quest for efficiency, we experiment with CNNs on the 2D triangular-lattice and 3D tetrahedral-lattice.

* BMVC 2015  
View paper onarxiv icon

Share this with someone who'll enjoy it:

Twitter IconFacebook IconLinkedin IconWhatsapp IconMessenger Icon