LAUSR

Abstract Facial expression details are important visual cues to interpret expressions, which are also hard to be synthesized. Since human eyes are more sensitive to the subtle variation of color than that of gray scales, expression details are especially obvious in color images. We propose a novel facial expression transfer method to synthesize realistic colorful facial expressions with source-specific expression details and the target identity feature. First, we choose YUV color space to represent the expression images. In Y channel of the color space, the expression image of the source object is transformed into frequency domain through fast Fourier transform. Then, the expression details including micro-expressions of the source object are extracted through analyzing their frequency distribution. Finally, those expression details are stitched smoothly to the target object with the modified Poisson image editing method. The transferred result in Y channel is combined with U and V channels of the warped target expression to synthesize the colorful realistic expressions of the target object, which reduces the effect of illumination and skin color variations. Experiments on the Multi-PIE database show that our method has higher perceptual quality over several state-of-the-art methods.