Dataset

LIP

Loose Inertial Poser upper-body jacket IMU mocap (n=5, 4 Xsens MTi-3, 60 Hz native)

LIP (Loose Inertial Poser) captures upper-body motion with four Xsens MTi-3 IMUs sewn into a loose-wear jacket (n=5, 60 Hz native), addressing everyday wear rather than strap-tight mocap. The CVPR 2024 paper also describes a Secondary Motion AutoEncoder used to model clothing-induced IMU motion. The public GitHub release includes the LIP_Dataset folder; a dataset licence is not stated there.

At a glance
Type
Dataset
Licence
Not reported
Access
Not reported
Subjects
5
Signals
IMU
PPG sites
None
Setting
Lab
Wrist
Not reported
Raw waveforms
Not reported
Models
Updated
Nov 13, 2026

Original description

Existing wearable motion capture methods typically demand tight on-body fixation (often using straps) for reliable sensing, limiting their application in everyday life. In this paper, we introduce Loose Inertial Poser, a novel motion capture solution with high wearing comfortableness, by integrating four Inertial Measurement Units (IMUs) into a loose-wear jacket. Specifically, we address the challenge of scarce loose-wear IMU training data by proposing a Secondary Motion AutoEncoder (SeMo-AE) that learns to model and synthesize the effects of secondary motion between the skin and loose clothing on IMU data. SeMo-AE is leveraged to generate a diverse synthetic dataset of loose-wear IMU data to augment training for the pose estimation network and significantly improve its accuracy. For validation, we collected a dataset with various subjects and 2 wearing styles (zipped and unzipped). Experimental results demonstrate that our approach maintains high-quality real-time posture estimation even in loose-wear scenarios. Our dataset and code are available at: https://github.com/ZuoCX1966/Loose-Inertial-Poser

Verbatim fromSemantic Scholar· Abstract via Semantic Scholar; © the authors/publisher

LIP: ChatPPG research summary card

Key numbers

5
Subjects
1
Reference labels
ACTIVITY

How it works

How LIP works: Devices & body sites → Signals recorded → TasksDevices & body sites: None (PPG site). Signals recorded: LIP, 5 subjects, signals IMU. Tasks: Activity recognition.Devices & body sitesNone: PPG siteNonePPG siteSignals recordedLIP5 subjectsxyzIMUTasksActivity recognitionActivity recognition
Reference labels
activity

Papers and models using this dataset· 2

#92 of 173 most-used datasets by published papers and models · #41 of 79 IMU

Cite this dataset

Cite this dataset with the fields recorded here. Check it against the publisher before submitting.

LIP [Data set]. (n.d.). github. https://doi.org/10.1109/CVPR52733.2024.00215
@misc{liplooseinertial,
  title         = {{LIP}},
  howpublished  = {github},
  doi           = {10.1109/CVPR52733.2024.00215}
}

Cite the ChatPPG record

Cite the dated snapshot 2026-10 for a fixed, reproducible version. Please also cite the original publications listed above.

APA

ChatPPG. (2026). LIP: dataset record (Version 2026-10) [Data set]. ChatPPG Research Hub. https://chatppg.com/research/datasets/lip-loose-inertial-poser

BibTeX
@misc{chatppg_dataset_lip_loose_inertial_poser,
  author       = {{ChatPPG}},
  title        = {{LIP: dataset record}},
  year         = {2026},
  month        = nov,
  version      = {2026-10},
  howpublished = {\url{https://chatppg.com/research/datasets/lip-loose-inertial-poser}},
  note         = {ChatPPG Research Hub, Snapshot 2026-10, https://chatppg.com/research/snapshots/2026-10}
}
CITATION.cff
cff-version: 1.2.0
message: "If you use this resource, please cite it as below."
type: dataset
title: "LIP: dataset record"
authors:
  - name: "ChatPPG"
url: "https://chatppg.com/research/datasets/lip-loose-inertial-poser"
repository-artifact: "https://chatppg.com/research/snapshots/2026-10"
version: "2026-10"
date-released: "2026-11-13"

History

  1. Record updated