Markerless reconstruction and synthesis of dynamic facial expressions

In this paper we combine methods from the field of computer vision with surface editing techniques to generate animated faces, which are all in full correspondence to each other. The inputs for our system are synchronized video streams from multiple cameras. The system produces a sequence of triangle meshes with fixed connectivity, representing the dynamics of the captured face. By carefully taking all requirements and characteristics into account we decided for the proposed system design: We deform an initial face template using movements estimated from the video streams. To increase the robustness of the reconstruction, we use a morphable model as a shape prior to initialize a surfel fitting technique which is able to precisely capture face shapes not included in the morphable model. In the deformation stage, we use a 2D mesh based tracking approach to establish correspondences over time. We then reconstruct positions in 3D using the same surfel fitting technique, and finally use the reconstructed points to robustly deform the initially reconstructed face. We demonstrate the applicability of the tracked face template for automatic modeling and show how to use deformation transfer to attenuate expressions, blend expressions or how to build a statistical model, similar to a morphable model, on the dynamic movements.

Research highlights
► A carefully designed computer vision system reconstructs human faces from video data.
► 2D mesh tracking naturally handles movements in opposite directions (eyes, lips).
► Surfel fitting provides 3D constraints to track a 3D face model.
► Deformation transfer techniques transfer, attenuate and blend facial expressions.
► A statistical expression model is deduced from deformation gradients of triangles.