Existing 3D datasets that we can use for 3D CNN:
1. RGB-D devices: Google Tango, Microsoft Kinect, etc.(https://developer.microsoft.com/en-us/windows/kinect)
2. Lidar(https://en.wikipedia.org/wiki/Lidar)
3. 3D reconstruction from multiple images (https://en.wikipedia.org/wiki/3D_reconstruction_from_multiple_images)

Existing 3D datasets that we can use for 3D CNN:

One way to picture it is by using the following image:


University of Michigan - Ann Arbor

A 3D CNN is similar to a 2D CNN except that it differs in (non-exhaustive listing):
1- 3D Convolution Layers

2- 3D MaxPool Layers

3D Convolutional Neural Network

Step by Step Implementation: 3D Convolutional Neural Network in Keras
https://towardsdatascience.com/step-by-step-implementation-3d-convolutional-neural-network-in-keras-12efbdd7b130

Step by Step Implementation: 3D Convolutional Neural Network in Keras

How does 3d datas look like?

1- IRM data processing and therefore the inference

2- Autonomous vehicles

3- Distance estimation

Applications of 3D CNN

2d Maxpool Layers (2x2 filter) is about taking the maximum element of a small 2x2 square that we delimitate from the input.
Now in a 3d Maxpool (2x2x2), we look for the maximum element in a width 2 cube. This cube represents the space delimited by the 2x2x2 zone from the input

3d MaxPool Layers

A 2D convolution layer performs an entry per entry multiplication between the input and the filter, where the input and the filter are 2D matrices. 

In a 3D convolution layer, the same operation is performed on 3D inputs and the filters, such that:
- We multiply corresponding entries in the input and filter cubes and add up the results to determine the output entry.
- In addition to shifting (striding) the filter on two dimensions of the input matrix to perform the convolution operation, we also shift it in the third dimension.

For example, if we have a 4 x 4 x 4 input and a 3 x 3 x 3 filter, because we can shift the filter for only one entry per dimension, the output will be 2 x 2 x 2.

3D Convolution Layers

You are building a network layer whose input volume has size 32x32x32x16 (this volume has 16 channels), and applies convolutions with 32 filters of dimension 3x3x3 (no padding, stride 1).

Learn Before

Related

Learn After