Performance-driven animation of hand-drawn cartoon faces

摘要

We present a novel performance-driven approach to animating cartoon faces starting from pure 2D drawings. A 3D approximatenfacial model automatically built from front and side view master frames of character drawings is introduced tonenable the animated cartoon faces to be viewed from angles different from that in the input video. The expressive mappingsnare built by artificial neural network (ANN) trained from the examples of the real face in the video and the cartoon facialndrawings in the facial expression graph for a specific character. The learned mapping model makes the resultant facialnanimation to properly get the desired expressiveness, instead of a mere reproduction of the facial actions in the input videonsequence. Furthermore, the lit sphere, capturing the lighting in the painting artwork of faces, is utilized to color the cartoonnfaces in terms of the 3D approximate facial model, reinforcing the hand-drawn appearance of the resulting facial animation.nWe made a series of comparative experiments to test the effectiveness of our method by recreating the facial expression innthe commercial animation. The comparison results clearly demonstrate the superiority of our method not only in generatingnhigh quality cartoon-style facial expressions, but also in speeding up the animation production of cartoon faces. Copyrightn. 2011 John Wiley & Sons, Ltd.