Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2603.21327 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910063008940032 |
|---|---|
| author | Wu, Wenhan Guo, Zhishuai Chen, Chen Das, Srijan Xue, Hongfei Wang, Pu Lu, Aidong |
| author_facet | Wu, Wenhan Guo, Zhishuai Chen, Chen Das, Srijan Xue, Hongfei Wang, Pu Lu, Aidong |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_21327 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | KHMP: Frequency-Domain Kalman Refinement for High-Fidelity Human Motion Prediction Wu, Wenhan Guo, Zhishuai Chen, Chen Das, Srijan Xue, Hongfei Wang, Pu Lu, Aidong Computer Vision and Pattern Recognition 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. |
| title | KHMP: Frequency-Domain Kalman Refinement for High-Fidelity Human Motion Prediction |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2603.21327 |