Using a RGB image feed and a depth map, it is possible to project the colored pixels into three dimensions and create a point cloud. This tutorial uses a Microsoft Kinect, OpenCV's python bindings and Python-OpenGL. Alot of the code has been adapted from the freenect-glpclview example that comes with libfreenect.
Image registration is a way of aligning images so that they are orientated in such a way so that they provide greater detail. This is particularly useful in medical imaging, for example, matching a CT scan with the output of a MRI. Both layers provide intricate knowledge of the anatomy, however together, they increase resolution and detail of the image.