Motion Imitation for Monocular Videos
This work represents a simple method for motion transfer (i.e., given a source video of a subject [person] performing some movements or in motion, that movement/motion is transferred to amateur target in different motion). The pose is used as an intermediate representation to perform this translation. To transfer the motion of the source subject to the target subject, the pose is extracted from the source subject, and then the target subject is generated by applying the learned pose to-appearance mapping. To perform this translation, the video is considered as a set of images consisting of all the frames. Generative adversarial networks (GANs) are used to transfer the motion from source subject to the target subject. GANs are an evolving field of deep learning.