Analogous view transfer for gaze correction in video sequences

This paper provides a framework for doing facial gaze correction in video sequences. The proposed framework involves stages of face registration, face parameter mapping, and face synthesis. We introduce the concept of analogous views, and derive a novel formulation which extends view transfers based on epipolar geometry to cope with non-rigid motion. Additionally, a disparity mapping function is derived which is learned from training data and handles both spatial disparities as well as pixel-value changes. The disparity mapping function generalizes to facial expressions, illumination conditions and individuals not in the training set, as shown by the results obtained.