AI RESEARCH
An Elastic Shape Variational Autoencoder for Skeleton Pose Trajectories
arXiv CS.CV
•
ArXi:2605.09231v1 Announce Type: new Deep generative models provide flexible frameworks for modeling complex, structured data such as images, videos, 3D objects, and texts. However, when applied to sequences of human skeletons, standard variational autoencoders (VAEs) often allocate substantial capacity to nuisance factors-such as camera orientation, subject scale, viewpoint, and execution speed-rather than the intrinsic geometry of shapes and their motion.