Refining Diffusion Models for Motion Synthesis with an Acceleration Loss to Generate Realistic IMU Data

• URL: http://arxiv.org/abs/2512.08859v1
• Date: Tue, 09 Dec 2025 17:51:01 GMT
• Title: Refining Diffusion Models for Motion Synthesis with an Acceleration Loss to Generate Realistic IMU Data
• Authors: Lars Ole Häusler, Lena Uhlenberg, Göran Köber, Diyora Salimova, Oliver Amft,
• Abstract summary: We propose a text-to-IMU (inertial measurement unit) motion-synthesis framework to obtain realistic IMU data.<n>We fine-tune a pretrained diffusion model with an acceleration-based second-order loss (L_acc)<n>L_acc enforces consistency in the discrete second-order temporal differences of the generated motion.
• Score: 1.291843130404247
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: We propose a text-to-IMU (inertial measurement unit) motion-synthesis framework to obtain realistic IMU data by fine-tuning a pretrained diffusion model with an acceleration-based second-order loss (L_acc). L_acc enforces consistency in the discrete second-order temporal differences of the generated motion, thereby aligning the diffusion prior with IMU-specific acceleration patterns. We integrate L_acc into the training objective of an existing diffusion model, finetune the model to obtain an IMU-specific motion prior, and evaluate the model with an existing text-to-IMU framework that comprises surface modelling and virtual sensor simulation. We analysed acceleration signal fidelity and differences between synthetic motion representation and actual IMU recordings. As a downstream application, we evaluated Human Activity Recognition (HAR) and compared the classification performance using data of our method with the earlier diffusion model and two additional diffusion model baselines. When we augmented the earlier diffusion model objective with L_acc and continued training, L_acc decreased by 12.7% relative to the original model. The improvements were considerably larger in high-dynamic activities (i.e., running, jumping) compared to low-dynamic activities~(i.e., sitting, standing). In a low-dimensional embedding, the synthetic IMU data produced by our refined model shifts closer to the distribution of real IMU recordings. HAR classification trained exclusively on our refined synthetic IMU data improved performance by 8.7% compared to the earlier diffusion model and by 7.6% over the best-performing comparison diffusion model. We conclude that acceleration-aware diffusion refinement provides an effective approach to align motion generation and IMU synthesis and highlights how flexible deep learning pipelines are for specialising generic text-to-motion priors to sensor-specific tasks.

Related papers

• Optimization Benchmark for Diffusion Models on Dynamical Systems [1.1603243575080533]
  We benchmark recent optimization algorithms for training a diffusion model for denoising flow trajectories.<n>We observe that Muon and SOAP are highly efficient alternatives to AdamW (18% lower final loss)
  arXiv  Detail & Related papers  (2025-10-22T08:50:31Z)
• Mobility-Aware Asynchronous Federated Learning with Dynamic Sparsification [14.942677904783759]
  This paper develops a theoretical model to characterize the interplay among sparsification, model staleness and mobility-induced contact patterns.<n>We propose a mobility-aware dynamic sparsification algorithm that optimize the sparsification degree based on contact time and model staleness.<n>Compared with the state-of-the-art benchmarks, the MADS algorithm increases the image classification accuracy on the CIFAR-10 dataset by 8.76% and reduces the average displacement error in the Argoverse trajectory prediction dataset by 9.46%.
  arXiv  Detail & Related papers  (2025-06-08T23:58:32Z)
• FlowMo: Variance-Based Flow Guidance for Coherent Motion in Video Generation [51.110607281391154]
  FlowMo is a training-free guidance method for enhancing motion coherence in text-to-video models.<n>It estimates motion coherence by measuring the patch-wise variance across the temporal dimension and guides the model to reduce this variance dynamically during sampling.
  arXiv  Detail & Related papers  (2025-06-01T19:55:33Z)
• Joint Velocity-Growth Flow Matching for Single-Cell Dynamics Modeling [38.9381649903752]
  A destructive measurement technique and cell proliferation/death result in unpaired and unbalanced data between snapshots.<n>We propose Velocity-Growth Flow Matching, a novel paradigm that jointly learns state transition and mass growth of single-cell populations.<n> VGFM builds an ideal single-cell dynamics containing velocity of state and growth of mass, driven by a presented two-period dynamic understanding of the static semi-relaxed optimal transport.
  arXiv  Detail & Related papers  (2025-05-19T17:48:04Z)
• REWIND: Real-Time Egocentric Whole-Body Motion Diffusion with Exemplar-Based Identity Conditioning [95.07708090428814]
  We present REWIND, a one-step diffusion model for real-time, high-fidelity human motion estimation from egocentric image inputs.<n>We introduce cascaded body-hand denoising diffusion, which effectively models the correlation between egocentric body and hand motions.<n>We also propose a novel identity conditioning method based on a small set of pose exemplars of the target identity, which further enhances motion estimation quality.
  arXiv  Detail & Related papers  (2025-04-07T11:44:11Z)
• Energy-Based Diffusion Language Models for Text Generation [126.23425882687195]
  Energy-based Diffusion Language Model (EDLM) is an energy-based model operating at the full sequence level for each diffusion step.<n>Our framework offers a 1.3$times$ sampling speedup over existing diffusion models.
  arXiv  Detail & Related papers  (2024-10-28T17:25:56Z)
• Bayesian-Optimized One-Step Diffusion Model with Knowledge Distillation for Real-Time 3D Human Motion Prediction [2.402745776249116]
  We propose training a one-step multi-layer perceptron-based (MLP-based) diffusion model for motion prediction using knowledge distillation and Bayesian optimization. Our model can significantly improve the inference speed, achieving real-time prediction without noticeable degradation in performance.
  arXiv  Detail & Related papers  (2024-09-19T04:36:40Z)
• Synthetic location trajectory generation using categorical diffusion models [50.809683239937584]
  Diffusion models (DPMs) have rapidly evolved to be one of the predominant generative models for the simulation of synthetic data. We propose using DPMs for the generation of synthetic individual location trajectories (ILTs) which are sequences of variables representing physical locations visited by individuals.
  arXiv  Detail & Related papers  (2024-02-19T15:57:39Z)
• Generative Modeling with Phase Stochastic Bridges [49.4474628881673]
  Diffusion models (DMs) represent state-of-the-art generative models for continuous inputs. We introduce a novel generative modeling framework grounded in textbfphase space dynamics Our framework demonstrates the capability to generate realistic data points at an early stage of dynamics propagation.
  arXiv  Detail & Related papers  (2023-10-11T18:38:28Z)
• How Much is Enough? A Study on Diffusion Times in Score-based Generative Models [76.76860707897413]
  Current best practice advocates for a large T to ensure that the forward dynamics brings the diffusion sufficiently close to a known and simple noise distribution. We show how an auxiliary model can be used to bridge the gap between the ideal and the simulated forward dynamics, followed by a standard reverse diffusion process.
  arXiv  Detail & Related papers  (2022-06-10T15:09:46Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.