Geometric Neural Distance Fields for Learning Human Motion Priors
This work addresses the challenge of robust and physically plausible 3D human motion recovery for applications in animation and robotics, representing a novel method rather than an incremental improvement.
The paper tackled the problem of generating realistic 3D human motion by introducing Neural Riemannian Motion Fields (NRMF), a novel motion prior that models motion using neural distance fields on geometric spaces, resulting in significant gains in tasks like denoising and motion in-betweening across multiple input modalities.
We introduce Neural Riemannian Motion Fields (NRMF), a novel 3D generative human motion prior that enables robust, temporally consistent, and physically plausible 3D motion recovery. Unlike existing VAE or diffusion-based methods, our higher-order motion prior explicitly models the human motion in the zero level set of a collection of neural distance fields (NDFs) corresponding to pose, transition (velocity), and acceleration dynamics. Our framework is rigorous in the sense that our NDFs are constructed on the product space of joint rotations, their angular velocities, and angular accelerations, respecting the geometry of the underlying articulations. We further introduce: (i) a novel adaptive-step hybrid algorithm for projecting onto the set of plausible motions, and (ii) a novel geometric integrator to "roll out" realistic motion trajectories during test-time-optimization and generation. Our experiments show significant and consistent gains: trained on the AMASS dataset, NRMF remarkably generalizes across multiple input modalities and to diverse tasks ranging from denoising to motion in-betweening and fitting to partial 2D / 3D observations.