Reconstructing 3D face from a single 2D image

Published 12 February 2008

Researchers develop software to make the 3D reconstruction of a face from a single 2D image faster and more accurate; this will be especially useful for recovering 3D shapes when there is only one image to work from, such as an image from a CCTV camera

A stranger once approached Oscar Wilde on a London street, grabbed his hand and shook it vigorously, then patted him on the back, saying: “How are you, Oscar?” To which Wilde responded: “I don’t know your face, but your manner is familiar.” Wilde could have used facial recognition technology, especially the one being developed by scientists at York University, who work on software to make the 3D reconstruction of a face from a single 2D image faster and more accurate. Dr. William Smith, a lecturer in computer vision at York, aims to combine the advantages of two face-recognition techniques to challenge the most advanced method for recovering 3D shapes when there is only one image to work from, such as an image from a CCTV camera. One of the techniques, which is also the most sophisticated, uses a morphable statistical model of facial appearance, while the approach that Smith has been working on uses classical shape-from-shading techniques. The Engineer reports that the statistical approach works by taking a model and adjusting parameters to try to fit the model to an image. “This is something that has been really big in computer vision,” said Smith. “The idea is that faces are all quite similar and you can learn the variations in face shape by looking at loads of examples.”

According to Smith, the advantages of this technique are that it works well on real images and can recognize a large number of different faces. A weakness, however, is that the shape it recovers is completely determined by what it has learned earlier, which means it is not able to recover atypical features which it has not come across before. This is where the latter face recognition technique is relevant. “Shape-from-shading is a really old idea which goes back to the 1950s and 1960s — they used it to try and recover the topography of the moon before they landed there. Our method uses the information in the image, so we interpret the changes in brightness and darkness as changes in the direction of the surface of the face. The strength of our method is in recovering local shape, for example, wrinkles on the skin or some subtle difference in nose shape,” he said.

The details missed by the model approach vary depending on factors such as the position of the face. “For example, if you view the face