We addressed one of the main challenges of existing example-based retargeting methods, the need for a large number of accurate training examples to define the correspondence between source and target expression spaces. In complement of a realtime face tracking and modeling algorithm, we developed a novel system for animation retargeting that allows learning a high-quality mapping between motion capture data and arbitrary target characters. We extended this approach removing the need of a user-specific training or calibration, or any other form of manual assistance, by modeling online a 3D user-specific dynamic face model.
Robust and efficient tracking is achieved by building an accurate 3D expression model of the user's face who is scanned in a predefined set of facial expressions. The main drawback of this approach in the context of consumer applications is the need for an offline user-specific training. This led to unprecedented face tracking quality on a low cost consumer level device. We introduce a novel face tracking algorithm that combines geometry and texture registration with pre-recorded animation priors in a single optimization. This permits to formulate the motion tracking problem as a 2D/3D non-rigid registration of a deformable model to the input data. RGB-D devices typically capture an image and a depth map. Recent technological advances in RGB-D devices, such as Microsoft Kinect, brought new hopes for realtime, portable, and affordable systems allowing to capture facial expressions as well as hand and body motions.
As a result, creating and animating high-quality digital avatars entails long turn-around times and substantial production costs. However, these methods typically require complex acquisition systems and substantial manual post-processing. Digital humans are often created through a combination of 3D scanning, appearance acquisition, and motion capture, leading to stunning results in recent feature films. The high complexity of human geometry and motion dynamics, and the high sensitivity of the human visual system to variations and subtleties in faces and bodies make the 3D acquisition and reconstruction of humans in motion a challenging task. Capturing and processing human geometry, appearance, and motion is at the core of computer graphics, computer vision, and human-computer interaction.
0 kommentar(er)
