Facial 3D Reconstruction

3D face reconstruction has applications in computer vision, such as facial pose and expression estimation. In this example, an unguided volumetric regression model from the Wolfram Neural Net Repository is used to estimate the 3D shape of a face. See more details for this network here.

Evaluate the network on a face image. The network output is converted into a 3D image.

Resize the 3D volume to have the same width and height as the 2D image.

Multiply the original image with each slice to assign the proper gray level.

Reconstruct the 3D image from the list of slices.

Related Examples

de es fr ja ko pt-br zh