KHMP: Frequency-Domain Kalman Refinement for High-Fidelity Human Motion Prediction
This addresses the need for smooth and physically plausible human motion predictions in applications like animation or robotics, representing a new paradigm rather than an incremental improvement.
The paper tackled the problem of high-frequency jitter and temporal discontinuities in stochastic human motion prediction by introducing KHMP, a framework that uses an adaptive Kalman filter in the DCT domain and training-time physical constraints, achieving state-of-the-art accuracy on Human3.6M and HumanEva-I datasets.
Stochastic human motion prediction aims to generate diverse, plausible futures from observed sequences. Despite advances in generative modeling, existing methods often produce predictions corrupted by high-frequency jitter and temporal discontinuities. To address these challenges, we introduce KHMP, a novel framework featuring an adaptiveKalman filter applied in the DCT domain to generate high-fidelity human motion predictions. By treating high-frequency DCT coefficients as a frequency-indexed noisy signal, the Kalman filter recursively suppresses noise while preserving motion details. Notably, its noise parameters are dynamically adjusted based on estimated Signal-to-Noise Ratio (SNR), enabling aggressive denoising for jittery predictions and conservative filtering for clean motions. This refinement is complemented by training-time physical constraints (temporal smoothness and joint angle limits) that encode biomechanical principles into the generative model. Together, these innovations establish a new paradigm integrating adaptive signal processing with physics-informed learning. Experiments on the Human3.6M and HumanEva-I datasets demonstrate that KHMP achieves state-of-the-art accuracy, effectively mitigating jitter artifacts to produce smooth and physically plausible motions.