CharacterGAN: Few-Shot Keypoint Character Animation and Reposing
This work provides a method for animating and reposing characters with very limited training data, which is beneficial for artists and animators working with custom or rare character designs.
CharacterGAN is a generative model that can be trained on 8-15 samples of a character to generate novel poses based on keypoint locations. It addresses disocclusions through a novel layering approach and uses an adaptive scaling method to combine layer features, outperforming recent baselines in creating realistic animations.
We introduce CharacterGAN, a generative model that can be trained on only a few samples (8 - 15) of a given character. Our model generates novel poses based on keypoint locations, which can be modified in real time while providing interactive feedback, allowing for intuitive reposing and animation. Since we only have very limited training samples, one of the key challenges lies in how to address (dis)occlusions, e.g. when a hand moves behind or in front of a body. To address this, we introduce a novel layering approach which explicitly splits the input keypoints into different layers which are processed independently. These layers represent different parts of the character and provide a strong implicit bias that helps to obtain realistic results even with strong (dis)occlusions. To combine the features of individual layers we use an adaptive scaling approach conditioned on all keypoints. Finally, we introduce a mask connectivity constraint to reduce distortion artifacts that occur with extreme out-of-distribution poses at test time. We show that our approach outperforms recent baselines and creates realistic animations for diverse characters. We also show that our model can handle discrete state changes, for example a profile facing left or right, that the different layers do indeed learn features specific for the respective keypoints in those layers, and that our model scales to larger datasets when more data is available.