AAM 25D

Generative Face Alignment Through 2.5D Active Appearance Models

Videos

Pedro Martins, Rui Caseiro, Jorge Batista
Institute of Systems and Robotics (ISR)
University of Coimbra, Portugal



Efficient Simultaneous Forwards Additive (ESFA) fitting algorithm


Video 1: 2.5D AAM fitting using the Efficient Simultaneous Forwards Additive (ESFA) algorithm. Each image show the input frame overlaid with the projected mesh and tree different views of the current 3D mesh s.


Efficient Robust Normalization Forwards Additive (ERNFA) fitting algorithm


Video 2: Robust 2.5D AAM fitting using the Efficient Robust Normalization Forwards Additive (ERNFA) algorithm. The weight mask is shown on the right. The scale parameters were estimated assuming that there always exists 10% of outliers.


Efficient Robust Simultaneous Forwards Additive (ERSFA) fitting algorithm


Video 3: Robust 2.5D AAM fitting using the Efficient Robust Simultaneous Forwards Additive (ERSFA) algorithm. The weight mask is shown on the bottom-right. The scale parameters were estimated from the fitting error MAD on the images of the training set. The black triangles of the face mesh are in occlusion.


Fitting on the 3D Dynamic Facial Expression Database (BU-4DFE) using ESFA fitting algorithm


Video 4: Some examples of BU-4DFE dataset used for the evaluation of the 3D recovered shape when using the 2.5D AAM. The BU-4DFE dataset includes high resolution 3D dense reconstructions of video sequences of several individuals showing the six prototypic facial expressions namely, anger, disgust, happiness, fear, sadness, and surprise. The 3D facial expressions were captured at 25 frames per second where each expression sequence contains about 100 frames (resolution of 1040x1392 per frame).


The Talking Face Sequence using the ERSFA fitting algorithm


Video 5: Qualitative 3D shape recovery on the Talking Face video sequence using the Efficient Robust Simultaneous Forwards Additive (ERSFA) algorithm.