A 3D Morphable Eye Region Model for Gaze Estimation

Morphable face models are a powerful tool in computer vision and graphics, but have previously failed to model the eye accurately due to complexities in its material and motion. We present a new multi-part model of the eye that includes a morphable model of the facial eye region, as well as an anatomy-based eyeball model. It is the first morphable model that accurately captures eye region shape, since it was built from high-quality head scans. It is also the first to allow independent movement of the eyeball, since we treat it as a separate part. To showcase our model we present a new method for illuminationand head-pose–invariant gaze estimation from a single RGB image. We fit our model to images through analysis-by-synthesis, solving for eye region shape, texture, eyeball pose, and scene illumination simultaneously. The fitted eyeball pose parameters are then used to estimate gaze direction. Through evaluation on two standard datasets we show that our method generalizes well to both webcam and high-quality camera images, and outperforms the state-ofthe-art CNN method achieving a gaze estimation accuracy of 9.43◦ in the challenging user-independent gaze estimation task.