Pose-Robust 3D Facial Landmark Estimation from a Single 2D Image

An algorithm is presented that estimates 3D facial landmark coordinates and occlusion state from a single 2D image. Unlike previous approaches, we divide the 3D cascaded shape regression problem into a set of viewpoint domains, which helps avoid problems in the optimization, such as local minima at test time, and averaging conflicting gradient directions in the domain maps during training. These problems are especially important to address in the 3D case, where a wider range of head poses is expected. Parametric shape models are used and are shown to have several desirable qualities compared to the recent trend of modeling shape nonparametrically. Results show quantitatively that our approach is significantly more accurate than recent work.