Single-Shot Freestyle Dance Reenactment
This work provides a method for animating a single image with arbitrary dance video sequences, which is useful for content creation and entertainment industries.
This paper addresses the problem of transferring dance motions from a source dancer to a target person using a single image of the target. The proposed method generates a novel sequence of realistic frames, capturing natural motion and appearance, and achieves significantly better visual quality than previous methods.
The task of motion transfer between a source dancer and a target person is a special case of the pose transfer problem, in which the target person changes their pose in accordance with the motions of the dancer. In this work, we propose a novel method that can reanimate a single image by arbitrary video sequences, unseen during training. The method combines three networks: (i) a segmentation-mapping network, (ii) a realistic frame-rendering network, and (iii) a face refinement network. By separating this task into three stages, we are able to attain a novel sequence of realistic frames, capturing natural motion and appearance. Our method obtains significantly better visual quality than previous methods and is able to animate diverse body types and appearances, which are captured in challenging poses, as shown in the experiments and supplementary video.