KHMP: Frequency-Domain Kalman Refinement for High-Fidelity Human Motion Prediction

Wenhan Wu; Zhishuai Guo; Chen Chen; Srijan Das; Hongfei Xue; Pu Wang; Aidong Lu

cs.CVMar 22, 2026

KHMP: Frequency-Domain Kalman Refinement for High-Fidelity Human Motion Prediction

Authors: Wenhan Wu, Zhishuai Guo, Chen Chen, Srijan Das, Hongfei Xue, Pu Wang, Aidong Lu

Organizations: School of Engineering, Yunnan University, Kunming, Yunnan, China · Department of Computer Science, University of North Carolina at Charlotte, Charlotte, NC, USA · Department of Computer Science, Northern Illinois University, DeKalb, IL, USA · Institute of Artificial Intelligence, University of Central Florida, Orlando, FL, USA

Abstract

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.

Figures & tables

Figure 1: Comparison illustrating motion prediction for the jogging action. Previous frameworks (top) often generate predictions exhibiting physical implausibility (highlighted by red circles) and temporal discontinuity (abrupt pose transitions). KHMP (bottom) integrates physical constraints during training and adaptive frequency-Kalman refinement during inference to produce more plausible and temporally smoother motion sequences.

Figure 2: Overview of the proposed KHMP framework. During training (left), a VAE backbone model learns with standard losses augmented by structured Physical Constraints (Sec. 4.2 ) for enhanced realism. During inference (right), raw predictions are processed by the Adaptive Frequency-Kalman Refinement module (Sec. 4.3 ). This module uses SNR -based parameter adjustments and recursive Kalman filtering to adaptively smooth high-frequency noise, yielding refined predictions.

Method	Venue	HumanEva-I					Human3.6M
Method	Venue	APD $\uparrow$	ADE $\downarrow$	FDE $\downarrow$	MMADE $\downarrow$	MMFDE $\downarrow$	APD $\uparrow$	ADE $\downarrow$	FDE $\downarrow$	MMADE $\downarrow$	MMFDE $\downarrow$
ERD [ 8 ]	ICCV 2015	0	0.382	0.461	0.521	0.595	0	0.722	0.969	0.776	0.995
DeLiGAN [ 9 ]	CVPR 2017	2.177	0.306	0.322	0.385	0.371	6.509	0.483	0.534	0.520	0.545
BoM [ 3 ]	CVPR 2018	2.846	0.271	0.279	0.373	0.351	6.265	0.448	0.533	0.514	0.544
DLow [ 34 ]	ECCV 2020	4.855	0.251	0.268	0.362	0.339	11.741	0.425	0.518	0.495	0.531
DSF [ 33 ]	ICLR 2020	4.538	0.273	0.290	0.364	0.340	9.330	0.493	0.592	0.550	0.599

Table 1: Quantitative comparison between KHMP and published state-of-the-art methods. The bold and underlined values represent the best and second-best results, respectively. * indicates our re-implementation of the baseline [ 30 ] , trained with KHMP’s hyperparameters but without physical constraints (Sec. 4.2 ) and Frequency-Kalman refinement (Sec. 4.3 ).

Table 2: Comprehensive ablation studies and quantitative analysis of the KHMP framework. (a) Analysis of the full framework components. (b) Ablation on structured physical losses. (c) Comparison of Frequency-Kalman refinement strategies. (d) Fixed Frequency Suppression [ 29 ] vs. our Adaptive Frequency-Kalman Refinement on HumanEva-I. (e) Quantitative evaluation of jitter reduction.

Panel of Figure 3 — Figure 3: Sensitivity analysis of hyperparameters: $k_{0}$ , $\lambda_{Q}$ , $\lambda_{R}$ , $\lambda_{\text{angle}}$ , and $\lambda_{\text{temporal}}$ .

Panel of Figure 4 — Figure 4: Visual comparison of joint trajectories demonstrating KHMP’s refinement over the baseline across two distinct actions. The top two rows ( a - d ) present examples from the Gesturing action (Ankle, Upper Arm, Wrist, and Shin). The bottom two rows ( e - h ) present examples from the Walking action (Ankle, Shin, Thigh, and Wrist). Within each subfigure, the first column displays the 3D trajectory, while the subsequent columns show the X, Y, and Z coordinates over time. Across all examples, the baseline prediction (red line) exhibits noticeable high-frequency jitter, whereas KHMP (blue line) significantly smooths the trajectory, closely adhering to the ground truth (green dashed line) and demonstrating effective refinement. Best viewed by zooming in.

Panel of Figure 5 — Figure 5: Visual comparison highlighting KHMP’s enhanced prediction quality over the baseline across various actions ( Boxing , Jogging , Walking , and Gesturing ). The figure showcases KHMP’s ability to correct physical implausibility often present in raw generative model outputs. In the examples shown, red arrows indicate issues in baseline predictions, while blue boxes highlight the corresponding smoother and more coherent KHMP results. Best viewed by zooming in. We also provide video demos in the SupMat .

Appendix figures & tables4 assets

Supplementary material from the paper’s appendix.

Appendix

Figure 6: Behavior of adaptive Kalman filter parameters versus estimated SNR (

\text{SNR}_{\text{est}}

). As signal quality increases (higher SNR), observation noise

R

decreases sharply, while process noise

Q

decreases moderately. Consequently, the Kalman gain

K_{k}

increases, shifting the filter’s behavior from strong smoothing (low SNR, noisy signals) towards detail preservation (high SNR, clean signals).

Loss Term	SLD-HMP	Ours
$\lambda_{\text{recon}}$	8.0	11.0
$\lambda_{\text{h}}$	10.0	16.0
$\lambda_{\text{mm}}$	4.0	0.1
$\lambda_{\text{d}}$	16.0	0.63
$\lambda_{\text{limb}}$	50.0	0.5
$\lambda_{\text{nf}}$	0.002	0.002

Appendix

Table 3: Loss weights configuration.

Method	HumanEva-I					Human3.6M
Method	APD $\uparrow$	ADE $\downarrow$	FDE $\downarrow$	MMADE $\downarrow$	MMFDE $\downarrow$	APD $\uparrow$	ADE $\downarrow$	FDE $\downarrow$	MMADE $\downarrow$	MMFDE $\downarrow$
MotionWavelet [ 7 ]	4.171	0.235	0.213	0.304	0.280	6.506	0.376	0.408	0.466	0.443
KHMP (Ours)	7.481	0.188	0.204	0.301	0.291	9.235	0.349	0.441	0.436	0.468

Appendix

Table 4: Quantitative comparison between KHMP and MotionWavelet on HumanEva-I and Human3.6M datasets. Best results are highlighted in bold.

Figure 7: Additional qualitative comparison between Baseline and KHMP predictions for selected frames from Jogging and Gesturing actions. Red arrows highlight implausible poses in the baseline, while blue boxes show the refined and more realistic results from KHMP.

Human Motion Prediction

Human motion prediction forecasts how people will move, supporting applications from animation and activity understanding to safe robot interaction.

See all 53 papers

AdvMT: Adversarial Motion Transformer for Long-term Human Motion Prediction
Jan 10, 2024Sarmad Idrees, Seokman Sohn, Jongeun ChoiTransformer Human Motion Generation
School of Mechanical Engineering, Yonsei University, Seoul 03722, Korea · Power Generation Lab, Korea Power Research Institute, 105, Munji-Ro, Yuseong-Gu, Daejeon, 34056, South Korea
SimpliHuMoN: Simplifying Human Motion Prediction
Mar 4, 2026Aadya Agrawal, Alexander SchwingHuman Motion Prediction Human Trajectory Prediction
University of Illinois Urbana-Champaign, USA
Gaussian-Mixture Latent Flow for Stochastic 3D Human Motion Prediction
Aug 21, 2026Yue Ma, Frederick W. B. Li, Xiaohui LiangHuman Motion Prediction Flow-Based Generative Modeling
Beihang University · Durham University · Zhongguancun Laboratory

Jan 10, 2024J/K move · Enter open · S save

AdvMT: Adversarial Motion Transformer for Long-term Human Motion Prediction

Sarmad Idrees, Seokman Sohn, Jongeun Choi

School of Mechanical Engineering, Yonsei University, Seoul 03722, Korea · Power Generation Lab, Korea Power Research Institute, 105, Munji-Ro, Yuseong-Gu, Daejeon, 34056, South Korea

Transformer Human Motion Generation Human Motion Prediction Trajectory Prediction

Open paper AskPDF arXiv

Human motion prediction is a crucial capability for advanced robotic systems that interact with humans. In facilities with dynamic human-robot collaboration settings, robots must anticipate human movements to ensure safety, prevent collisions, and optimize cooperative tasks. Traditionally, motion forecasting is treated as a sequential modeling problem using historical pose data, but achieving long-term accuracy and physical realism remains challenging. We present Adversarial Motion Transformer (AdvMT), a novel approach that integrates a Transformer-based motion encoder with a temporal continuity discriminator to address these challenges. The Transformer captures rich spatio-temporal dependencies across human joints, while adversarial training with a continuity discriminator enforces smooth, natural motion trajectories that adhere to biomechanical constraints. Our training scheme includes a bone-length consistency term and adversarial loss to reduce common artifacts like pose freezing or unnatural transitions. In experiments on the Human3.6M motion dataset, AdvMT achieves state-of-the-art long-horizon prediction accuracy while also delivering robust short-term predictions. These improvements strengthen the prediction foundation for physical AI in manufacturing and human-robot collaboration, where anticipating human motion is a prerequisite for safe and efficient robot coordination.

Abstract

Human Motion Prediction

Explore similar work

AdvMT: Adversarial Motion Transformer for Long-term Human Motion Prediction

SimpliHuMoN: Simplifying Human Motion Prediction

Gaussian-Mixture Latent Flow for Stochastic 3D Human Motion Prediction