GGMotion: Group Graph Dynamics-Kinematics Networks for Human Motion Prediction
This addresses the challenge of generating physically plausible human motions for applications in animation and robotics, representing an incremental advance over existing graph-based methods.
The paper tackled the problem of human motion prediction by modeling physical dependencies between joints to generate more realistic motions, achieving significant performance improvements on standard benchmarks like Human3.6M, CMU-Mocap, and 3DPW.
Human motion is a continuous physical process in 3D space, governed by complex dynamic and kinematic constraints. Existing methods typically represent the human pose as an abstract graph structure, neglecting the intrinsic physical dependencies between joints, which increases learning difficulty and makes the model prone to generating unrealistic motions. In this paper, we propose GGMotion, a group graph dynamics-kinematics network that models human topology in groups to better leverage dynamics and kinematics priors. To preserve the geometric equivariance in 3D space, we propose a novel radial field for the graph network that captures more comprehensive spatio-temporal dependencies by aggregating joint features through spatial and temporal edges. Inter-group and intra-group interaction modules are employed to capture the dependencies of joints at different scales. Combined with equivariant multilayer perceptrons (MLP), joint position features are updated in each group through parallelized dynamics-kinematics propagation to improve physical plausibility. Meanwhile, we introduce an auxiliary loss to supervise motion priors during training. Extensive experiments on three standard benchmarks, including Human3.6M, CMU-Mocap, and 3DPW, demonstrate the effectiveness and superiority of our approach, achieving a significant performance margin in short-term motion prediction. The code is available at https://github.com/inkcat520/GGMotion.git.