For each subject we capture a raw head scan in neutral expression with an active stereo system (3dMD LLC, Atlanta). The multi-camera system consists of six gray-scale stereo camera pairs, six color cameras, five speckle pattern projectors, and six white LED panels. The reconstructed 3D geometry contains about 120K vertices for each subject. Each subject wears a hair cap during scanning to avoid occlusions and scanner noise in the face or neck region due to hair.
The challenge for all categories is to reconstruct a neutral 3D face given a single monocular image. Note that facial expressions are present in several images, which requires methods to disentangle identity and expression to evaluate the quality of the predicted identity.
The participants can receive their results before submission to a conference or journal by mentioning "private (under submission)" in their email. We will not update the results in the website. Everything will be kept confidential. Later the participants can resend the mail mentioning "update *** results" with the predicted meshes again. We will update our website with their results. "***" is the acronym of the method the participants are proposing. They should also provide a reference to their method/paper which we can link in this section. The cumulative error curves for the current compared methods.