Neural Kinematic Networks for Unsupervised Motion Retargetting

We propose a recurrent neural network architecture with a Forward Kinematics layer and cycle consistency based adversarial training objective for unsupervised motion retargetting. Our network captures high-level properties of an input motion by the forward kinematics layer and adapts them for a target character with different skeleton bone lengths (e.g., shorter, longer arms etc.). Collecting paired motion training sequences from different characters is expensive. Instead, our network utilizes cycle consistency to learn to solve the Inverse Kinematics problem in an unsupervised manner. Our method works online that adapts the motion sequence on-the-fly as new frames are received. In our experiments, we use the Mixamo animation data 1 to test our method for a variety of motions and characters and achieve state-of-the-art results. We also demonstrate motion retargetting from monocular human videos to 3D characters using a off-the-shelf 3D pose estimator. * Most of this work was done during Ruben’s internship at Adobe. 1https://www.mixamo.com. See details in Section 5.