Leveraging the Talent of Hand Animators to Create Three-Dimensional Animation
Jessica Hodgins (Disney Research Los Angeles, Disney Research Pittsburgh)
Yaser Sheikh (Carnegie Mellon University)
Eakta Jain (Carnegie Mellon University)
The skills required to create three-dimensional animation using computer software are quite different from those required to create hand animation with paper and pencil. The three dimensional medium has several advantages over the traditional medium it is easy to relight the scene, render it from different view points, and add physical simulations. We present a method to leverage the talent of traditionally trained hand animators to create three-dimensional animation of human motion, while allowing them to work in the medium that is familiar to them. The input to our algorithm is a set of hand-animated frames. Our key insight is to use motion capture data as a source of domain knowledge and ‘lift’ the two-dimensional animation to three dimensions, while maintaining the unique style of the input animation. Our approach 3D animation which captures (1) the pose of the character in each frame, and (2) the timing of the series of frames. The input to our algorithm is a sequence of hand animated frames. Our key insight is to leverage motion capture data as a source of domain knowledge to aid in resolving ambiguities and noise in the 2D drawings. We show that 3D animation can be created by modifying motion capture animation with style elements from the hand-drawn frames. We modify the timing of the motion capture poses to match the hand-drawn poses via dynamic time warping and introduce a translation and scale invariant pose descriptor to capture pose information. We present results on a variety of hand animations including a ballet sequence, a stylized sneaky walk and a jumping jacks sequence. We also evaluate our algorithm quantitatively using a motion capture sequence as input.