PaperarXiv:2611.09323
DiffusionRef-IMU: Guide-Anchored Residual Diffusion for Cross-Location Inertial Measurement Unit Translation
arXiv preprint
TL;DR
Two-stage source-to-target IMU translation: a FiLM U-Net Direct guide, then diffusion on the residual only. 5-fold held-out activity-location nRMSE 0.0875 vs 0.0903 Direct (5/5 folds); 4-step DDIM 47.6 ms on T4; zero-shot transfer mixed (wins Grouvel, loses Saldana).
Abstract
Cross-location variation in wearable inertial measurement unit (IMU) signals complicates learning when measurements from a desired target body location are unavailable. This study proposes DiffusionRef-IMU, a two-stage cross-location translation framework in which a deterministic Direct network first estimates the target signal and a guide-anchored residual diffusion model refines only the remaining target discrepancy. The evaluation comprises five subject-disjoint activity-location composition-held-out folds, capacity-matched deterministic and flow-based residual baselines, source-only activity conditioning, computational ablation, and true zero-shot evaluation on two independent datasets. DiffusionRef-IMU with 16-step deterministic DDIM achieved a mean nRMSE of 0.087538 +/- 0.004922, compared with 0.090262 for Direct, 0.088847 for deterministic residual refinement, and 0.088417 for eight-step CompFlow, and outperformed each baseline in all five folds. Four-step DDIM retained a mean nRMSE of 0.087820 at 47.62 ms per window, providing a favourable quality-computation trade-off. Replacing ground-truth activity conditioning with a source-only activity predictor (macro-F1 0.8473) increased 16-step DiffusionRef nRMSE only to 0.088190. True zero-shot evaluation produced mixed results: DiffusionRef was marginally favourable on Grouvel2025 but remained worse than Direct on Salda\~na2025. Overall, guide-anchored residual diffusion improves controlled cross-location reconstruction while revealing clear limits in zero-shot external transfer.
Verbatim from arXiv (opens in a new tab) · arXiv metadata (abstracts are released under CC0)
Results on ChatPPG leaderboards
All leaderboardsNo results from this paper on ChatPPG leaderboards yet. Browse the leaderboards.
Tasks & signals
Tasks
Signals
Keywords
How it works
Cite this paper
Hafiz, M. M. G., Simi, S. A., Islam, M. R., & Mridha, M. F. (2026). DiffusionRef-IMU: Guide-Anchored Residual Diffusion for Cross-Location Inertial Measurement Unit Translation. arXiv preprint. https://arxiv.org/abs/2611.09323
Hafiz, M. M. Golam, Safia Akter Simi, Md. Rakibul Islam, and M. F. Mridha. 2026. "DiffusionRef-IMU: Guide-Anchored Residual Diffusion for Cross-Location Inertial Measurement Unit Translation." arXiv preprint. https://arxiv.org/abs/2611.09323.
Hafiz, M. M. G., Simi, S. A., Islam, M. R. and Mridha, M. F. (2026) 'DiffusionRef-IMU: Guide-Anchored Residual Diffusion for Cross-Location Inertial Measurement Unit Translation', arXiv preprint. Available at: https://arxiv.org/abs/2611.09323
Hafiz, M. M. Golam, et al. "DiffusionRef-IMU: Guide-Anchored Residual Diffusion for Cross-Location Inertial Measurement Unit Translation." arXiv preprint, 2026. https://arxiv.org/abs/2611.09323.
M. M. G. Hafiz, S. A. Simi, M. R. Islam, and M. F. Mridha, "DiffusionRef-IMU: Guide-Anchored Residual Diffusion for Cross-Location Inertial Measurement Unit Translation," arXiv preprint, 2026, [Online]. Available: https://arxiv.org/abs/2611.09323.
@misc{hafiz2026diffusionrefimu,
title = {{DiffusionRef-IMU: Guide-Anchored Residual Diffusion for Cross-Location Inertial Measurement Unit Translation}},
author = {Hafiz, M. M. Golam and Simi, Safia Akter and Islam, Md. Rakibul and Mridha, M. F.},
year = {2026},
howpublished = {arXiv preprint},
eprint = {2611.09323},
archivePrefix = {arXiv}
}Added to the ChatPPG research hub
