Human Motion Prediction Using Manifold-Aware Wasserstein GAN
This work addresses motion prediction for human pose analysis, offering incremental improvements by applying a novel method to a known bottleneck.
The paper tackles the challenges of discontinuity and long-term performance deterioration in human motion prediction by modeling 3D human poses as trajectories on a sphere manifold, using a manifold-aware Wasserstein GAN. It outperforms state-of-the-art methods on CMU MoCap and Human 3.6M datasets, with qualitative results showing smooth predicted motions.
Human motion prediction aims to forecast future human poses given a prior pose sequence. The discontinuity of the predicted motion and the performance deterioration in long-term horizons are still the main challenges encountered in current literature. In this work, we tackle these issues by using a compact manifold-valued representation of human motion. Specifically, we model the temporal evolution of the 3D human poses as trajectory, what allows us to map human motions to single points on a sphere manifold. To learn these non-Euclidean representations, we build a manifold-aware Wasserstein generative adversarial model that captures the temporal and spatial dependencies of human motion through different losses. Extensive experiments show that our approach outperforms the state-of-the-art on CMU MoCap and Human 3.6M datasets. Our qualitative results show the smoothness of the predicted motions.