HMD-Poser: On-Device Real-time Human Motion Tracking from Scalable Sparse Observations
Not on the map. Why?
Abstract (arXiv)
It is especially challenging to achieve real-time human motion tracking on a standalone VR Head-Mounted Display (HMD) such as Meta Quest and PICO. In this paper, we propose HMD-Poser, the first unified approach to recover full-body motions using scalable sparse observations from HMD and body-worn IMUs. In particular, it can support a variety of input scenarios, such as HMD, HMD+2IMUs, HMD+3IMUs, etc. The scalability of inputs may accommodate users' choices for both high tracking accuracy and easy-to-wear. A lightweight temporal-spatial feature learning network is proposed in HMD-Poser to guarantee that the model runs in real-time on HMDs. Furthermore, HMD-Poser presents online body shape estimation to improve the position accuracy of body joints. Extensive experimental results on the challenging AMASS dataset show that HMD-Poser achieves new state-of-the-art results in both accuracy and real-time performance. We also build a new free-dancing motion dataset to evaluate HMD-Poser's on-device performance and investigate the performance gap between synthetic data and real-captured sensor data. Finally, we demonstrate our HMD-Poser with a real-time Avatar-driving application on a commercial HMD. Our code and free-dancing motion dataset are available https://pico-ai-team.github.io/hmd-poser
Key facts. Cited by 22 papers in the map (data through 7 Oct 2026). Builds on 41 of its 59 references that are in the map. First posted on arXiv 6 Mar 2024.
Builds on
41 of 59 references.
References · 41
- 2017Attention Is All You Needcited by 59,932
- 2019Expressive Body Capture: 3D Hands, Face, and Body from a Single Imagecited by 1,600
- 2019AMASS: Archive of Motion Capture as Surface Shapescited by 1,208
- 2018On the Continuity of Rotation Representations in Neural Networkscited by 1,186
- 2017End-to-end Recovery of Human Shape and Posecited by 883
- 2021Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learningcited by 882
- 2016Keep it SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Imagecited by 692
- 2019VIBE: Video Inference for Human Body Pose and Shape Estimationcited by 615
- 2021PARE: Part Attention Regressor for 3D Human Body Estimationcited by 334
- 2018Learning 3D Human Dynamics from Videocited by 315
- 20213D Human Pose Estimation with Spatial and Temporal Transformerscited by 271
- 2022MixSTE: Seq2seq Mixed Spatio-Temporal Encoder for 3D Human Pose Estimation in Videocited by 158
29 more
- 2021MHFormer: Multi-Hypothesis Transformer for 3D Human Pose Estimationcited by 151
- 2022Physical Inertial Poser (PIP): Physics-aware Real-time Human Motion Tracking from Sparse Inertial Sensorscited by 144
- 2017Sparse Inertial Poser: Automatic 3D Human Pose Estimation from Sparse IMUscited by 108
- 2022AvatarPoser: Articulated Full-Body Pose Tracking from Sparse Motion Sensingcited by 107
- 2023Avatars Grow Legs: Generating Smooth Human Motion from Sparse Tracking Inputs with Diffusion Modelcited by 104
- 20233D Human Pose Estimation via Intuitive Physicscited by 100
- 2018DoubleFusion: Real-time Capture of Human Performances with Inner Body Shapes from a Single Depth Sensorcited by 95
- 2022Ego-Body Pose Estimation via Ego-Head Pose Estimationcited by 93
- 2022QuestSim: Human Motion Tracking from Sparse Sensors with Simulated Avatarscited by 74
- 2021Estimating Egocentric 3D Human Pose in Global Spacecited by 56
- 2022UnrealEgo: A New Dataset for Robust Egocentric 3D Human Motion Capturecited by 56
- 2022FLAG: Flow-based 3D Avatar Generation from Sparse Observationscited by 54
- 2021THUNDR: Transformer-based 3D HUmaN Reconstruction with Markerscited by 50
- 2023EgoLocate: Real-time Motion Capture, Localization, and Mapping with Sparse Body-mounted Sensorscited by 48
- 2023NIKI: Neural Inverse Kinematics with Invertible Neural Networks for 3D Human Pose and Shape Estimationcited by 45
- 2023Realistic Full-Body Tracking from Sparse Observations via Joint-Level Modelingcited by 41
- 2021VoxelTrack: Multi-Person 3D Human Pose Estimation and Tracking in the Wildcited by 39
- 2022Trajectory Optimization for Physics-Based Reconstruction of 3d Human Pose from Monocular Videocited by 37
- 2019Multiview-Consistent Semi-Supervised Learning for 3D Human Pose Estimationcited by 31
- 2022Neural MoCon: Neural Motion Control for Physically Plausible Human Motion Capturecited by 31
- 2021SOMA: Solving Optical Marker-Based MoCap Automaticallycited by 30
- 2021RobustFusion: Robust Volumetric Performance Reconstruction under Human-object Interactions from Monocular RGBD Streamcited by 26
- 2023QuestEnvSim: Environment-Aware Simulated Motion Tracking from Sparse Sensorscited by 26
- 2022Ray3D: ray-based 3D human pose estimation for monocular absolute 3D localizationcited by 25
- 2023SparsePoser: Real-time Full-body Motion Reconstruction from Sparse Datacited by 20
- 2022Learning Variational Motion Prior for Video-based Motion Capturecited by 17
- 2023HMD-NeMo: Online 3D Avatar Motion Generation From Sparse Observationscited by 17
- 2023Fusing Monocular Images and Sparse IMU Signals for Real-time Human Motion Capturecited by 17
- 2021Real-time RGBD-based Extended Body Pose Estimationcited by 12
Built on by
Citing papers per year: 2024: 3; 2025: 9; 2026: 10.
22 papers.
Sort:
By area:
- 2025Ego4o: Egocentric Human Motion Capture and Understanding from Multi-Modal Inputcited by 17
- 2024EMHI: A Multimodal Egocentric Human Motion Dataset with HMD and Body-Worn IMUscited by 12
- 2024EnvPoser: Environment-aware Realistic Human Motion Estimation from Sparse Observations with Uncertainty Modelingcited by 11
- 2025From Sparse Signal to Smooth Motion: Real-Time Motion Generation with Rolling Prediction Modelscited by 11
- 2024Estimating Ego-Body Pose from Doubly Sparse Egocentric Video Datacited by 8
- 2025UMotion: Uncertainty-driven Human Motion Estimation from Inertial and Ultra-wideband Unitscited by 5
- 2025Human Motion Capture from Loose and Sparse Inertial Sensors with Garment-aware Diffusion Modelscited by 5
- 2025Mojito: LLM-Aided Motion Instructor with Jitter-Reduced Inertial Tokenscited by 4
- 2025ECHO: Ego-Centric modeling of Human-Object interactionscited by 4
- 2026Ground Reaction Inertial Poser: Physics-based Human Motion Capture from Sparse IMUs and Insole Pressure Sensorscited by 2
- 2025KineST: A Kinematics-guided Spatiotemporal State Space Model for Human Motion Tracking from Sparse Signalscited by 1
- 2026Egocentric Visibility-Aware Human Pose Estimationcited by 1
10 more
- 2026Towards Real-World Wearable Motion Reconstructioncited by 1
- 2025Mem-MLP: Real-Time 3D Human Motion Generation from Sparse Inputscited by 0
- 2025OmniEgoCap: Camera-Agnostic Sequence-Level Egocentric Motion Reconstructioncited by 0
- 2026EgoPoseVR: Spatiotemporal Multi-Modal Reasoning for Egocentric Full-Body Pose in Virtual Realitycited by 0
- 2026AtomicMotion: Learning Human Motion From Different Human Partscited by 0
- 2026MotionMAR: Multi-scale Auto-Regressive Human Motion Reconstruction from Sparse Observationscited by 0
- 2026IMU-HOI: A Symbiotic Framework for Coherent Human-Object Interaction and Motion Capture via Contact-Conscious Inertial Fusioncited by 0
- 2026EgoExoMoCap: Distributed Ego-Exo Human Motion Capturecited by 0
- 2026One Sensor, Whole Body - 3D Body Pose from a Single Consumer Earbud IMUcited by 0
- 2026Reliability-Gated Fusion of Consumer Head and Foot IMUs for Lower-Body 3D Posecited by 0
- 2026Reliability-Gated Fusion of Consumer Head and Foot IMUs for Lower-Body 3D Pose28 Sep 2026
- 2026One Sensor, Whole Body - 3D Body Pose from a Single Consumer Earbud IMU28 Sep 2026
- 2026EgoExoMoCap: Distributed Ego-Exo Human Motion Capture17 Jul 2026
- 2026Towards Real-World Wearable Motion Reconstruction8 Jul 2026
- 2026IMU-HOI: A Symbiotic Framework for Coherent Human-Object Interaction and Motion Capture via Contact-Conscious Inertial Fusion26 Jun 2026
- 2026MotionMAR: Multi-scale Auto-Regressive Human Motion Reconstruction from Sparse Observations22 Jun 2026
- 2026AtomicMotion: Learning Human Motion From Different Human Parts21 May 2026
- 2026Ground Reaction Inertial Poser: Physics-based Human Motion Capture from Sparse IMUs and Insole Pressure Sensors17 Mar 2026
- 2026Egocentric Visibility-Aware Human Pose Estimation27 Feb 2026
- 2026EgoPoseVR: Spatiotemporal Multi-Modal Reasoning for Egocentric Full-Body Pose in Virtual Reality5 Feb 2026
- 2025OmniEgoCap: Camera-Agnostic Sequence-Level Egocentric Motion Reconstruction22 Dec 2025
- 2025KineST: A Kinematics-guided Spatiotemporal State Space Model for Human Motion Tracking from Sparse Signals18 Dec 2025
10 more
- 2025Mem-MLP: Real-Time 3D Human Motion Generation from Sparse Inputs20 Nov 2025
- 2025ECHO: Ego-Centric modeling of Human-Object interactions29 Aug 2025
- 2025Human Motion Capture from Loose and Sparse Inertial Sensors with Garment-aware Diffusion Models18 Jun 2025
- 2025UMotion: Uncertainty-driven Human Motion Estimation from Inertial and Ultra-wideband Units14 May 2025
- 2025Ego4o: Egocentric Human Motion Capture and Understanding from Multi-Modal Input11 Apr 2025
- 2025From Sparse Signal to Smooth Motion: Real-Time Motion Generation with Rolling Prediction Models7 Apr 2025
- 2025Mojito: LLM-Aided Motion Instructor with Jitter-Reduced Inertial Tokens22 Feb 2025
- 2024EnvPoser: Environment-aware Realistic Human Motion Estimation from Sparse Observations with Uncertainty Modeling13 Dec 2024
- 2024Estimating Ego-Body Pose from Doubly Sparse Egocentric Video Data5 Nov 2024
- 2024EMHI: A Multimodal Egocentric Human Motion Dataset with HMD and Body-Worn IMUs30 Aug 2024
- 2025Ego4o: Egocentric Human Motion Capture and Understanding from Multi-Modal Inputcited by 17
- 2024EMHI: A Multimodal Egocentric Human Motion Dataset with HMD and Body-Worn IMUscited by 12
- 2024EnvPoser: Environment-aware Realistic Human Motion Estimation from Sparse Observations with Uncertainty Modelingcited by 11
- 2025From Sparse Signal to Smooth Motion: Real-Time Motion Generation with Rolling Prediction Modelscited by 11
- 2025UMotion: Uncertainty-driven Human Motion Estimation from Inertial and Ultra-wideband Unitscited by 5
- 2025Mojito: LLM-Aided Motion Instructor with Jitter-Reduced Inertial Tokenscited by 4
- 2025ECHO: Ego-Centric modeling of Human-Object interactionscited by 4
- 2026Ground Reaction Inertial Poser: Physics-based Human Motion Capture from Sparse IMUs and Insole Pressure Sensorscited by 2
- 2025KineST: A Kinematics-guided Spatiotemporal State Space Model for Human Motion Tracking from Sparse Signalscited by 1
- 2026Egocentric Visibility-Aware Human Pose Estimationcited by 1
- 2026Towards Real-World Wearable Motion Reconstructioncited by 1
- 2025Mem-MLP: Real-Time 3D Human Motion Generation from Sparse Inputscited by 0
12 most cited of 20 All 20 (JSON)
- 2026Reliability-Gated Fusion of Consumer Head and Foot IMUs for Lower-Body 3D Pose28 Sep 2026
- 2026One Sensor, Whole Body - 3D Body Pose from a Single Consumer Earbud IMU28 Sep 2026
- 2026EgoExoMoCap: Distributed Ego-Exo Human Motion Capture17 Jul 2026
- 2026Towards Real-World Wearable Motion Reconstruction8 Jul 2026
- 2026IMU-HOI: A Symbiotic Framework for Coherent Human-Object Interaction and Motion Capture via Contact-Conscious Inertial Fusion26 Jun 2026
- 2026MotionMAR: Multi-scale Auto-Regressive Human Motion Reconstruction from Sparse Observations22 Jun 2026
- 2026AtomicMotion: Learning Human Motion From Different Human Parts21 May 2026
- 2026Ground Reaction Inertial Poser: Physics-based Human Motion Capture from Sparse IMUs and Insole Pressure Sensors17 Mar 2026
- 2026Egocentric Visibility-Aware Human Pose Estimation27 Feb 2026
- 2026EgoPoseVR: Spatiotemporal Multi-Modal Reasoning for Egocentric Full-Body Pose in Virtual Reality5 Feb 2026
- 2025OmniEgoCap: Camera-Agnostic Sequence-Level Egocentric Motion Reconstruction22 Dec 2025
- 2025KineST: A Kinematics-guided Spatiotemporal State Space Model for Human Motion Tracking from Sparse Signals18 Dec 2025
12 newest of 20 All 20 (JSON)