pith. sign in

arxiv: 2606.26741 · v1 · pith:HZ43Q2RAnew · submitted 2026-06-25 · 💻 cs.RO · cs.CV

PressMimic: Pressure-Guided Motion Capture and Control for Humanoid Robot Imitation

Yi Lu , Shenghao Ren , Tianyu Xiong , Zhaoxiang Li , Jiaqi Li , He Zhang , Tao Yu , Qiu Shen
show 1 more author
Xun Cao
This is my paper

Pith reviewed 2026-06-26 05:07 UTC · model grok-4.3

classification 💻 cs.RO cs.CV
keywords humanoid robotsmotion imitationpressure sensingphysical groundingmultimodal fusionreinforcement learningcontact dynamicsmotion capture
0
0 comments X

The pith

Pressure readings from the floor resolve vision ambiguities and enforce stable contacts when humanoids copy human motion.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper claims that pressure measurements supply a physical grounding signal that connects perception to control, letting humanoid robots imitate human motion without the usual artifacts of sliding feet or floor penetration. It introduces a full pipeline that fuses pressure with RGB images to estimate 3D pose and global motion, then feeds pressure-derived signals into a reinforcement-learning policy so the robot reproduces realistic contact patterns. A supporting dataset supplies the required synchronized RGB, pressure, and motion-capture recordings. If this grounding works, imitation shifts from purely kinematic copying to physically consistent reproduction that respects support and contact forces. Readers should care because existing vision-only pipelines often produce motions that look correct in simulation yet fail on real hardware.

Core claim

The central claim is that pressure serves as an effective physical grounding signal, bridging perception and control for physically consistent humanoid motion imitation. In the perception stage, the FRAPPE++ model fuses RGB and pressure to jointly estimate 3D pose and global motion, with pressure providing explicit contact and support constraints that resolve vision ambiguities. In the control stage, a pressure-supervised policy incorporates pressure-derived signals into reinforcement learning so that execution matches observed contact patterns. Experiments on the MotionPRO dataset demonstrate gains in motion-estimation accuracy, trajectory consistency, and execution stability.

What carries the argument

The PressMimic framework, which routes pressure data through both a multimodal perception model (FRAPPE++) and a pressure-supervised control policy (PSP) to enforce physical contact constraints.

If this is right

  • Motion estimation becomes more accurate because pressure supplies explicit support constraints that vision alone cannot resolve.
  • Trajectory consistency rises as the policy learns to reproduce the pressure patterns recorded during human motion.
  • Execution stability improves, reducing foot sliding and floor penetration in real-robot runs.
  • Perception and control become unified through one physical signal instead of being optimized separately.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • The pressure-grounding approach could be tested on other contact-rich behaviors such as carrying objects or climbing stairs without changing the core fusion method.
  • If pressure maps remain informative across different floor materials, the perception model might transfer to new environments with minimal retraining.
  • One could check whether retrofitting existing vision-only motion datasets with simulated pressure yields comparable gains, avoiding new hardware collection.

Load-bearing premise

Pressure data can be reliably captured, synchronized with RGB and motion capture, and fused to provide explicit contact and support constraints that resolve vision ambiguities.

What would settle it

Compare imitation performance on identical tasks with and without pressure inputs; if the pressure-free version matches or exceeds accuracy, consistency, and stability, the claim that pressure supplies necessary grounding would fail.

Figures

Figures reproduced from arXiv: 2606.26741 by He Zhang, Jiaqi Li, Qiu Shen, Shenghao Ren, Tao Yu, Tianyu Xiong, Xun Cao, Yi Lu, Zhaoxiang Li.

Figure 1
Figure 1. Figure 1: We propose PressMimic, a unified framework that integrates pressure into both motion capture and motion control for humanoid motion imitation. By [PITH_FULL_IMAGE:figures/full_fig_p001_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: Overview of PressMimic. Given synchronized RGB video and pressure sequences, PressMimic estimates human body motion, retargets it to the humanoid robot, and executes it via a learned control policy. Pressure signals enhance motion estimation accuracy and provide auxiliary contact supervision for the control policy, as indicated by the orange dashed arrow. dependencies within the current window while incorp… view at source ↗
Figure 3
Figure 3. Figure 3: The framework of FRAPPE++. Pressure and RGB video are processed by the SPE and image encoder respectively, followed by TCAM to model spatiotemporal dependencies within each modality. FCAM then fuses the two modalities via cross-attention, where image features serve as key and value while pressure features serve as query. The fused representation is fed into a regressor to estimate SMPL parameters. This all… view at source ↗
Figure 4
Figure 4. Figure 4: Humanoid motion imitation under pressure-supervised policy (PSP). Human pose and plantar pressure serve as dual inputs: the pose is retargeted to robot reference motion and concatenated with the current state as policy input, while pressure drives a two-stage curriculum that first imitates the human pressure offset and then adapts to the robot’s own optimal contact distribution via EMA updates. Building up… view at source ↗
Figure 5
Figure 5. Figure 5: The architecture of our motion capture system for dataset collection. [PITH_FULL_IMAGE:figures/full_fig_p007_5.png] view at source ↗
Figure 6
Figure 6. Figure 6: Hierarchal distribution of 400 motion types. [PITH_FULL_IMAGE:figures/full_fig_p007_6.png] view at source ↗
Figure 7
Figure 7. Figure 7: Qualitative comparison with methods for human pose estimation. [PITH_FULL_IMAGE:figures/full_fig_p008_7.png] view at source ↗
Figure 8
Figure 8. Figure 8: Real-world humanoid motion imitation results. Rows show execution results under different reference sources and control policies. Low-quality references (GVHMR, WHAM) lead to twisted postures and instability, while FRAPPE++ with BeyondMimic achieves stable but conservative foot placement. FRAPPE++ with PSP (Ours) produces stable execution with more natural foot contact dynamics (white circles), validating … view at source ↗
read the original abstract

Humanoid motion imitation requires not only accurate perception of human kinematics but also faithful reproduction of physical interactions with the environment. However, existing pipelines rely primarily on vision-based motion capture and kinematic imitation, largely ignoring contact dynamics, leading to artifacts such as foot sliding, floor penetration, and unstable behaviors. In this work, we revisit humanoid motion imitation from the perspective of physical grounding and leverage pressure as a unified modality across perception and control. We present PressMimic, a framework that integrates pressure into the full pipeline from motion capture to humanoid control. In the perception stage, we introduce FRAPPE++, a multimodal model that fuses RGB and pressure to jointly estimate 3D pose and global motion, where pressure provides explicit contact and support constraints to resolve ambiguity in vision-based estimation. In the control stage, we propose a pressure-supervised policy (PSP) that incorporates pressure-derived signals into reinforcement learning, enabling physically consistent contact patterns during execution. We further construct MotionPRO, a large-scale dataset with synchronized RGB, pressure, and motion capture data. Experiments show that pressure improves motion estimation accuracy, trajectory consistency, and execution stability. These results demonstrate that pressure serves as an effective physical grounding signal, bridging perception and control for physically consistent humanoid motion imitation.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

1 major / 0 minor

Summary. The paper presents PressMimic, a framework for humanoid motion imitation that incorporates pressure sensing as a physical grounding modality across the full pipeline. In perception, FRAPPE++ fuses RGB and pressure to estimate 3D pose and global motion while using pressure for explicit contact and support constraints. In control, a pressure-supervised policy (PSP) incorporates pressure-derived signals into reinforcement learning for consistent contact patterns. The work also introduces the MotionPRO dataset containing synchronized RGB, pressure, and motion capture data. The central claim is that pressure improves motion estimation accuracy, trajectory consistency, and execution stability relative to vision-only methods.

Significance. If the empirical claims are substantiated with quantitative evidence, the work would be significant for humanoid robotics by showing how a single additional modality (pressure) can address common artifacts in kinematic imitation such as foot sliding and instability, while providing a unified signal from perception through control. The release of a large-scale synchronized multimodal dataset would also be a concrete enabling contribution for the community.

major comments (1)
  1. [Abstract] Abstract: The assertion that 'Experiments show that pressure improves motion estimation accuracy, trajectory consistency, and execution stability' supplies no quantitative metrics, ablation results, baseline comparisons, or implementation details. This absence is load-bearing for evaluating whether the central claim that pressure serves as an effective physical grounding signal holds.

Simulated Author's Rebuttal

1 responses · 0 unresolved

We thank the referee for the constructive feedback and positive assessment of the work's potential significance. We address the single major comment below and will revise the manuscript accordingly.

read point-by-point responses

  1. Referee: [Abstract] Abstract: The assertion that 'Experiments show that pressure improves motion estimation accuracy, trajectory consistency, and execution stability' supplies no quantitative metrics, ablation results, baseline comparisons, or implementation details. This absence is load-bearing for evaluating whether the central claim that pressure serves as an effective physical grounding signal holds.

    Authors: We agree that the abstract statement would be strengthened by explicit quantitative support. The full manuscript provides these details in Section 4 (Experiments), including tables with pose estimation errors, trajectory metrics (e.g., foot sliding and penetration), stability scores, ablations isolating the pressure modality, and comparisons against vision-only baselines, along with implementation specifics for FRAPPE++ and PSP. To make the abstract self-contained and directly substantiate the central claim, we will revise it to incorporate key numerical highlights and pointers to the experimental results. This change will be reflected in the next version of the manuscript. revision: yes

Circularity Check

0 steps flagged

Empirical framework exhibits no derivational circularity

full rationale

The paper describes an empirical pipeline: FRAPPE++ fuses RGB+pressure for pose estimation, PSP uses pressure signals in RL for control, and MotionPRO supplies synchronized data. No equations, fitted parameters renamed as predictions, self-citations as load-bearing premises, or ansatzes imported via prior work are present in the provided text. Claims rest on experimental improvements rather than any closed logical reduction to inputs by construction. This is the expected honest outcome for a data-driven robotics framework.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

Abstract-only review provides no equations or implementation details; no free parameters, axioms, or invented entities can be identified.

pith-pipeline@v0.9.1-grok · 5776 in / 1017 out tokens · 26919 ms · 2026-06-26T05:07:22.956751+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

78 extracted references · 5 linked inside Pith

  1. [1]

    End-to- end recovery of human shape and pose,

    A. Kanazawa, M. J. Black, D. W. Jacobs, and J. Malik, “End-to- end recovery of human shape and pose,” inProceedings of the IEEE conference on computer vision and pattern recognition, 2018, pp. 7122– 7131

    2018

  2. [2]

    3d human pose estimation via intuitive physics,

    S. Tripathi, L. M ¨uller, C.-H. P. Huang, O. Taheri, M. J. Black, and D. Tzionas, “3d human pose estimation via intuitive physics,” inPro- ceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2023, pp. 4713–4725

    2023

  3. [3]

    Learning to reconstruct 3d human pose and shape via model-fitting in the loop,

    N. Kolotouros, G. Pavlakos, M. J. Black, and K. Daniilidis, “Learning to reconstruct 3d human pose and shape via model-fitting in the loop,” inProceedings of the IEEE/CVF international conference on computer vision, 2019, pp. 2252–2261

    2019

  4. [4]

    Cliff: Carrying location information in full frames into human pose and shape estimation,

    Z. Li, J. Liu, Z. Zhang, S. Xu, and Y . Yan, “Cliff: Carrying location information in full frames into human pose and shape estimation,” in European Conference on Computer Vision. Springer, 2022, pp. 590– 606

    2022

  5. [5]

    Reconstructing 3d human pose by watching humans in the mirror,

    Q. Fang, Q. Shuai, J. Dong, H. Bao, and X. Zhou, “Reconstructing 3d human pose by watching humans in the mirror,” inProceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2021, pp. 12 814–12 823

    2021

  6. [6]

    Hybrik: A hybrid analytical-neural inverse kinematics solution for 3d human pose and shape estimation,

    J. Li, C. Xu, Z. Chen, S. Bian, L. Yang, and C. Lu, “Hybrik: A hybrid analytical-neural inverse kinematics solution for 3d human pose and shape estimation,” inProceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2021, pp. 3383–3393

    2021

  7. [7]

    Humans in 4d: Reconstructing and tracking humans with transformers,

    S. Goel, G. Pavlakos, J. Rajasegaran, A. Kanazawa, and J. Malik, “Humans in 4d: Reconstructing and tracking humans with transformers,” inProceedings of the IEEE/CVF International Conference on Computer Vision, 2023, pp. 14 783–14 794

    2023

  8. [8]

    Deep inertial poser: Learning to reconstruct human pose from sparse inertial measurements in real time,

    Y . Huang, M. Kaufmann, E. Aksan, M. J. Black, O. Hilliges, and G. Pons-Moll, “Deep inertial poser: Learning to reconstruct human pose from sparse inertial measurements in real time,”ACM Transactions on Graphics (TOG), vol. 37, no. 6, pp. 1–15, 2018

    2018

  9. [9]

    Physical inertial poser (pip): Physics-aware real-time human motion tracking from sparse inertial sensors,

    X. Yi, Y . Zhou, M. Habermann, S. Shimada, V . Golyanik, C. Theobalt, and F. Xu, “Physical inertial poser (pip): Physics-aware real-time human motion tracking from sparse inertial sensors,” inProceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2022, pp. 13 167–13 178

    2022

  10. [10]

    Avatars grow legs: Generating smooth human motion from sparse tracking inputs with diffusion model,

    Y . Du, R. Kips, A. Pumarola, S. Starke, A. Thabet, and A. Sanakoyeu, “Avatars grow legs: Generating smooth human motion from sparse tracking inputs with diffusion model,” inProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 481– 490

    2023

  11. [11]

    Humanoid locomotion and manipulation: Current progress and challenges in control, planning, and learning,

    Z. Gu, J. Li, W. Shen, W. Yu, Z. Xie, S. McCrory, X. Cheng, A. Shamsah, R. Griffin, C. K. Liuet al., “Humanoid locomotion and manipulation: Current progress and challenges in control, planning, and learning,”IEEE/ASME Transactions on Mechatronics, vol. 31, no. 2, pp. 2300–2330, 2026

    2026

  12. [12]

    A review: Robust locomotion for biped humanoid robots,

    Y . Xie, B. Lou, A. Xie, and D. Zhang, “A review: Robust locomotion for biped humanoid robots,” inJournal of Physics: Conference Series, vol. 1487, no. 1. IOP Publishing, 2020, p. 012048

    2020

  13. [13]

    Humanoid robots and humanoid ai: Review, perspectives and directions,

    L. Cao, “Humanoid robots and humanoid ai: Review, perspectives and directions,”ACM Computing Surveys, vol. 58, no. 4, pp. 1–37, 2025

    2025

  14. [14]

    Motionpro: exploring the role of pressure in human mocap and beyond,

    S. Ren, Y . Lu, J. Huang, J. Zhao, H. Zhang, T. Yu, Q. Shen, and X. Cao, “Motionpro: exploring the role of pressure in human mocap and beyond,” inProceedings of the Computer Vision and Pattern Recognition Conference, 2025, pp. 27 760–27 770

    2025

  15. [15]

    Real-time imitation of human whole-body motions by humanoids,

    J. Koenemann, F. Burget, and M. Bennewitz, “Real-time imitation of human whole-body motions by humanoids,” in2014 IEEE International Conference on Robotics and Automation (ICRA). IEEE, 2014, pp. 2806–2812

    2014

  16. [16]

    Humanoid teleoperation using task-relevant haptic feedback,

    F. Abi-Farrajl, B. Henze, A. Werner, M. Panzirsch, C. Ott, and M. A. Roa, “Humanoid teleoperation using task-relevant haptic feedback,” in 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). IEEE, 2018, pp. 5010–5017

    2018

  17. [17]

    Telexistence and teleoperation for walking humanoid robots,

    M. Elobaid, Y . Hu, G. Romualdi, S. Dafarra, J. Babic, and D. Pucci, “Telexistence and teleoperation for walking humanoid robots,” inPro- ceedings of SAI Intelligent Systems Conference. Springer, 2019, pp. 1106–1121

    2019

  18. [18]

    Motion retargeting for humanoid robots based on simultaneous morphing parameter identification and motion optimization,

    K. Ayusawa and E. Yoshida, “Motion retargeting for humanoid robots based on simultaneous morphing parameter identification and motion optimization,”IEEE Transactions on Robotics, vol. 33, no. 6, pp. 1343– 1357, 2017

    2017

  19. [19]

    Adaptive whole-body manipulation in human-to-humanoid multi-contact motion retargeting,

    K. Otani and K. Bouyarmane, “Adaptive whole-body manipulation in human-to-humanoid multi-contact motion retargeting,” in2017 IEEE-RAS 17th International Conference on Humanoid Robotics (Hu- manoids). IEEE, 2017, pp. 446–453

    2017

  20. [20]

    Robust real-time whole- body motion retargeting from human to humanoid,

    L. Penco, B. Cl ´ement, V . Modugno, E. M. Hoffman, G. Nava, D. Pucci, N. G. Tsagarakis, J.-B. Mouret, and S. Ivaldi, “Robust real-time whole- body motion retargeting from human to humanoid,” in2018 IEEE- RAS 18th International Conference on Humanoid Robots (Humanoids). IEEE, 2018, pp. 425–432

    2018

  21. [21]

    Whole-body geometric retargeting for humanoid robots,

    K. Darvish, Y . Tirupachuri, G. Romualdi, L. Rapetti, D. Ferigo, F. J. A. Chavez, and D. Pucci, “Whole-body geometric retargeting for humanoid robots,” in2019 IEEE-RAS 19th International Conference on Humanoid Robots (Humanoids). IEEE, 2019, pp. 679–686

    2019

  22. [22]

    icub3 avatar system: Enabling remote fully immersive embodiment of humanoid robots,

    S. Dafarra, U. Pattacini, G. Romualdi, L. Rapetti, R. Grieco, K. Darvish, G. Milani, E. Valli, I. Sorrentino, P. M. Viceconteet al., “icub3 avatar system: Enabling remote fully immersive embodiment of humanoid robots,”Science Robotics, vol. 9, no. 86, p. eadh3834, 2024

    2024

  23. [23]

    Deepmimic: example-guided deep reinforcement learning of physics-based character skills,

    X. B. Peng, P. Abbeel, S. Levine, and M. van de Panne, “Deepmimic: example-guided deep reinforcement learning of physics-based character skills,”ACM Trans. Graph., vol. 37, no. 4, p. 143, 2018

    2018

  24. [24]

    Perpetual humanoid control for real-time simulated avatars,

    Z. Luo, J. Cao, K. Kitani, W. Xuet al., “Perpetual humanoid control for real-time simulated avatars,” inProceedings of the IEEE/CVF International Conference on Computer Vision, 2023, pp. 10 895–10 904

    2023

  25. [25]

    Universal humanoid motion representations for physics-based control,

    Z. Luo, J. Cao, J. Merel, A. Winkler, J. Huang, K. Kitani, and W. Xu, “Universal humanoid motion representations for physics-based control,” inInternational Conference on Learning Representations, vol. 2024, 2024, pp. 56 766–56 782

    2024

  26. [26]

    Masked- mimic: Unified physics-based character control through masked motion JOURNAL OF LATEX CLASS FILES, VOL. 14, NO. 8, AUGUST 2021 12 inpainting,

    C. Tessler, Y . Guo, O. Nabati, G. Chechik, and X. B. Peng, “Masked- mimic: Unified physics-based character control through masked motion JOURNAL OF LATEX CLASS FILES, VOL. 14, NO. 8, AUGUST 2021 12 inpainting,”ACM Transactions On Graphics (TOG), vol. 43, no. 6, pp. 1–21, 2024

    2021

  27. [27]

    Omni- grasp: Grasping diverse objects with simulated humanoids,

    Z. Luo, J. Cao, S. Christen, A. Winkler, K. Kitani, and W. Xu, “Omni- grasp: Grasping diverse objects with simulated humanoids,”Advances in Neural Information Processing Systems, vol. 37, pp. 2161–2184, 2024

    2024

  28. [28]

    Omniretarget: Interaction-preserving data generation for humanoid whole-body loco-manipulation and scene interaction,

    L. Yang, X. Huang, Z. Wu, A. Kanazawa, P. Abbeel, C. Sferrazza, C. K. Liu, R. Duan, and G. Shi, “Omniretarget: Interaction-preserving data generation for humanoid whole-body loco-manipulation and scene interaction,”arXiv preprint arXiv:2509.26633, 2025

    Pith/arXiv arXiv 2025

  29. [29]

    Track any motions under any disturbances,

    Z. Zhang, J. Guo, C. Chen, J. Wang, C. Lin, Y . Lian, H. Xue, Z. Wang, M. Liu, J. Lyuet al., “Track any motions under any disturbances,”arXiv preprint arXiv:2509.13833, 2025

    arXiv 2025

  30. [30]

    Sonic: Supersizing motion tracking for natural humanoid whole-body control,

    Z. Luo, Y . Yuan, T. Wang, C. Li, S. Chen, F. Castaneda, Z.-A. Cao, J. Li, D. Minor, Q. Benet al., “Sonic: Supersizing motion tracking for natural humanoid whole-body control,”arXiv preprint arXiv:2511.07820, 2025

    Pith/arXiv arXiv 2025

  31. [31]

    Omnih2o: Universal and dexterous human-to- humanoid whole-body teleoperation and learning,

    T. He, Z. Luo, X. He, W. Xiao, C. Zhang, W. Zhang, K. M. Kitani, C. Liu, and G. Shi, “Omnih2o: Universal and dexterous human-to- humanoid whole-body teleoperation and learning,” inConference on Robot Learning. PMLR, 2025, pp. 1516–1540

    2025

  32. [32]

    Kungfubot: Physics-based humanoid whole-body control for learning highly-dynamic skills,

    W. Xie, J. Han, J. Zheng, H. Li, X. Liu, J. Shi, W. Zhang, C. Bai, and X. Li, “Kungfubot: Physics-based humanoid whole-body control for learning highly-dynamic skills,”Advances in Neural Information Processing Systems, vol. 38, pp. 62 406–62 433, 2026

    2026

  33. [33]

    Asap: Aligning simulation and real-world physics for learning agile humanoid whole-body skills,

    T. He, J. Gao, W. Xiao, Y . Zhang, Z. Wang, J. Wang, Z. Luo, G. He, N. Sobanbab, C. Panet al., “Asap: Aligning simulation and real-world physics for learning agile humanoid whole-body skills,”arXiv preprint arXiv:2502.01143, 2025

    arXiv 2025

  34. [34]

    Bfm-zero: A promptable behavioral foundation model for humanoid control using unsupervised reinforcement learning,

    Y . Li, Z. Luo, T. Zhang, C. Dai, A. Kanervisto, A. Tirinzoni, H. Weng, K. Kitani, M. Guzek, A. Touatiet al., “Bfm-zero: A promptable behavioral foundation model for humanoid control using unsupervised reinforcement learning,”arXiv preprint arXiv:2511.04131, 2025

    arXiv 2025

  35. [35]

    Twist2: Scalable, portable, and holistic humanoid data collection system,

    Y . Ze, S. Zhao, W. Wang, A. Kanazawa, R. Duan, P. Abbeel, G. Shi, J. Wu, and C. K. Liu, “Twist2: Scalable, portable, and holistic humanoid data collection system,”arXiv preprint arXiv:2511.02832, 2025

    arXiv 2025

  36. [36]

    Beyondmimic: From motion tracking to versatile humanoid control via guided diffusion,

    Q. Liao, T. E. Truong, X. Huang, Y . Gao, G. Tevet, K. Sreenath, and C. K. Liu, “Beyondmimic: From motion tracking to versatile humanoid control via guided diffusion,”arXiv preprint arXiv:2508.08241, 2025

    Pith/arXiv arXiv 2025

  37. [37]

    A study of vicon system positioning performance,

    P. Merriaux, Y . Dupuis, R. Boutteau, P. Vasseur, and X. Savatier, “A study of vicon system positioning performance,”Sensors, vol. 17, no. 7, p. 1591, 2017

    2017

  38. [38]

    A review of accelerometer sensor and gyroscope sensor in imu sensors on motion capture,

    I. A. Faisal, T. W. Purboyo, and A. S. R. Ansori, “A review of accelerometer sensor and gyroscope sensor in imu sensors on motion capture,”J. Eng. Appl. Sci, vol. 15, no. 3, pp. 826–829, 2019

    2019

  39. [39]

    Questsim: Human motion tracking from sparse sensors with simulated avatars,

    A. Winkler, J. Won, and Y . Ye, “Questsim: Human motion tracking from sparse sensors with simulated avatars,” inSIGGRAPH Asia 2022 conference papers, 2022, pp. 1–8

    2022

  40. [40]

    Humanplus: Humanoid shadowing and imitation from humans,

    Z. Fu, Q. Zhao, Q. Wu, G. Wetzstein, and C. Finn, “Humanplus: Humanoid shadowing and imitation from humans,”arXiv preprint arXiv:2406.10454, 2024

    arXiv 2024

  41. [41]

    Exbody2: Advanced expressive humanoid whole-body control,

    M. Ji, X. Peng, F. Liu, J. Li, G. Yang, X. Cheng, and X. Wang, “Exbody2: Advanced expressive humanoid whole-body control,”arXiv preprint arXiv:2412.13196, 2024

    arXiv 2024

  42. [42]

    Vibe: Video inference for human body pose and shape estimation,

    M. Kocabas, N. Athanasiou, and M. J. Black, “Vibe: Video inference for human body pose and shape estimation,” inProceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2020, pp. 5253–5263

    2020

  43. [43]

    Beyond static features for temporally consistent 3d human pose and shape from a video,

    H. Choi, G. Moon, J. Y . Chang, and K. M. Lee, “Beyond static features for temporally consistent 3d human pose and shape from a video,” inProceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2021, pp. 1964–1973

    2021

  44. [44]

    Learning 3d human dynamics from video,

    A. Kanazawa, J. Y . Zhang, P. Felsen, and J. Malik, “Learning 3d human dynamics from video,” inProceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2019, pp. 5614–5623

    2019

  45. [45]

    Human mesh recov- ery from monocular images via a skeleton-disentangled representation,

    Y . Sun, Y . Ye, W. Liu, W. Gao, Y . Fu, and T. Mei, “Human mesh recov- ery from monocular images via a skeleton-disentangled representation,” inProceedings of the IEEE/CVF international conference on computer vision, 2019, pp. 5349–5358

    2019

  46. [46]

    Exploiting temporal context for 3d human pose estimation in the wild,

    A. Arnab, C. Doersch, and A. Zisserman, “Exploiting temporal context for 3d human pose estimation in the wild,” inProceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2019, pp. 3395–3404

    2019

  47. [47]

    Keep it smpl: Automatic estimation of 3d human pose and shape from a single image,

    F. Bogo, A. Kanazawa, C. Lassner, P. Gehler, J. Romero, and M. J. Black, “Keep it smpl: Automatic estimation of 3d human pose and shape from a single image,” inEuropean conference on computer vision. Springer, 2016, pp. 561–578

    2016

  48. [48]

    Expressive body capture: 3d hands, face, and body from a single image,

    G. Pavlakos, V . Choutas, N. Ghorbani, T. Bolkart, A. A. Osman, D. Tzionas, and M. J. Black, “Expressive body capture: 3d hands, face, and body from a single image,” inProceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2019, pp. 10 975–10 985

    2019

  49. [49]

    Weakly supervised 3d human pose and shape reconstruction with normalizing flows,

    A. Zanfir, E. G. Bazavan, H. Xu, W. T. Freeman, R. Sukthankar, and C. Sminchisescu, “Weakly supervised 3d human pose and shape reconstruction with normalizing flows,” inEuropean Conference on Computer Vision. Springer, 2020, pp. 465–481

    2020

  50. [50]

    Beyond weak perspective for monocular 3d human pose estimation,

    I. Kissos, L. Fritz, M. Goldman, O. Meir, E. Oks, and M. Kliger, “Beyond weak perspective for monocular 3d human pose estimation,” inEuropean Conference on Computer Vision. Springer, 2020, pp. 541– 554

    2020

  51. [51]

    Spec: Seeing people in the wild with an estimated camera,

    M. Kocabas, C.-H. P. Huang, J. Tesch, L. M ¨uller, O. Hilliges, and M. J. Black, “Spec: Seeing people in the wild with an estimated camera,” in Proceedings of the IEEE/CVF International Conference on Computer Vision, 2021, pp. 11 035–11 045

    2021

  52. [52]

    Zolly: Zoom focal length correctly for perspective- distorted human mesh reconstruction,

    W. Wang, Y . Ge, H. Mei, Z. Cai, Q. Sun, Y . Wang, C. Shen, L. Yang, and T. Komura, “Zolly: Zoom focal length correctly for perspective- distorted human mesh reconstruction,” inProceedings of the IEEE/CVF international conference on computer vision, 2023, pp. 3925–3935

    2023

  53. [53]

    Glamr: Global occlusion-aware human mesh recovery with dynamic cameras,

    Y . Yuan, U. Iqbal, P. Molchanov, K. Kitani, and J. Kautz, “Glamr: Global occlusion-aware human mesh recovery with dynamic cameras,” inProceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2022, pp. 11 038–11 049

    2022

  54. [54]

    Decoupling human and camera motion from videos in the wild,

    V . Ye, G. Pavlakos, J. Malik, and A. Kanazawa, “Decoupling human and camera motion from videos in the wild,” inProceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2023, pp. 21 222–21 232

    2023

  55. [55]

    Tram: Global trajectory and motion of 3d humans from in-the-wild videos,

    Y . Wang, Z. Wang, L. Liu, and K. Daniilidis, “Tram: Global trajectory and motion of 3d humans from in-the-wild videos,” inEuropean Conference on Computer Vision. Springer, 2024, pp. 467–487

    2024

  56. [56]

    Trace: 5d temporal regression of avatars with dynamic cameras in 3d environments,

    Y . Sun, Q. Bao, W. Liu, T. Mei, and M. J. Black, “Trace: 5d temporal regression of avatars with dynamic cameras in 3d environments,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 8856–8866

    2023

  57. [57]

    Wham: Reconstructing world-grounded humans with accurate 3d motion,

    S. Shin, J. Kim, E. Halilaj, and M. J. Black, “Wham: Reconstructing world-grounded humans with accurate 3d motion,” inProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024, pp. 2070–2080

    2024

  58. [58]

    World-grounded human motion recovery via gravity-view coordinates,

    Z. Shen, H. Pi, Y . Xia, Z. Cen, S. Peng, Z. Hu, H. Bao, R. Hu, and X. Zhou, “World-grounded human motion recovery via gravity-view coordinates,” inSIGGRAPH Asia 2024 Conference Papers, 2024, pp. 1–11

    2024

  59. [59]

    3d human pose estimation on a configurable bed from a pressure image,

    H. M. Clever, A. Kapusta, D. Park, Z. Erickson, Y . Chitalia, and C. C. Kemp, “3d human pose estimation on a configurable bed from a pressure image,” in2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). IEEE, 2018, pp. 54–61

    2018

  60. [60]

    Bodies at rest: 3d human pose and shape estimation from a pressure image using synthetic data,

    H. M. Clever, Z. Erickson, A. Kapusta, G. Turk, K. Liu, and C. C. Kemp, “Bodies at rest: 3d human pose and shape estimation from a pressure image using synthetic data,” inProceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2020, pp. 6215–6224

    2020

  61. [61]

    Multimodal in-bed pose and shape estimation under the blankets,

    Y . Yin, J. P. Robinson, and Y . Fu, “Multimodal in-bed pose and shape estimation under the blankets,” inProceedings of the 30th ACM International Conference on Multimedia, 2022, pp. 2411–2419

    2022

  62. [62]

    Bodymap-jointly predicting body mesh and 3d applied pressure map for people in bed,

    A. Tandon, A. Goyal, H. M. Clever, and Z. Erickson, “Bodymap-jointly predicting body mesh and 3d applied pressure map for people in bed,” inProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024, pp. 2480–2489

    2024

  63. [63]

    Simultaneously-collected multimodal lying pose dataset: Enabling in- bed human pose monitoring,

    S. Liu, X. Huang, N. Fu, C. Li, Z. Su, and S. Ostadabbas, “Simultaneously-collected multimodal lying pose dataset: Enabling in- bed human pose monitoring,”IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 45, no. 1, pp. 1106–1118, 2022

    2022

  64. [64]

    Bodypressure - inferring body pose and contact pressure from a depth image,

    H. M. Clever, P. L. Grady, G. Turk, and C. C. Kemp, “Bodypressure - inferring body pose and contact pressure from a depth image,”IEEE Trans. Pattern Anal. Mach. Intell., vol. 45, no. 1, pp. 137–153, 2023

    2023

  65. [65]

    Seeing through the tactile: 3d human shape estimation from temporal in-bed pressure images,

    Z. Wu, F. Xie, Y . Fang, Z. Liang, Q. Wan, Y . Xiong, and X. Cai, “Seeing through the tactile: 3d human shape estimation from temporal in-bed pressure images,”Proc. ACM Interact. Mob. Wearable Ubiquitous Technol., vol. 8, no. 2, pp. 86:1–86:39, 2024

    2024

  66. [66]

    Mmvp: A multimodal mocap dataset with vision and pressure sensors,

    H. Zhang, S. Ren, H. Yuan, J. Zhao, F. Li, S. Sun, Z. Liang, T. Yu, Q. Shen, and X. Cao, “Mmvp: A multimodal mocap dataset with vision and pressure sensors,” inProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024, pp. 21 842–21 852

    2024

  67. [67]

    Groundlink: A dataset unifying human body movement and ground reaction dynamics,

    X. Han, B. Senderling, S. To, D. Kumar, E. Whiting, and J. Saito, “Groundlink: A dataset unifying human body movement and ground reaction dynamics,” inSIGGRAPH Asia 2023 Conference Papers, 2023, pp. 1–10. JOURNAL OF LATEX CLASS FILES, VOL. 14, NO. 8, AUGUST 2021 13

    2023

  68. [68]

    Underpressure: Deep learning for foot contact detection, ground reaction force estimation and footskate cleanup,

    L. Mourot, L. Hoyet, F. L. Clerc, and P. Hellier, “Underpressure: Deep learning for foot contact detection, ground reaction force estimation and footskate cleanup,” inComputer Graphics F orum, vol. 41, no. 8. Wiley Online Library, 2022, pp. 195–206

    2022

  69. [69]

    From image to stability: Learning dynamics from human pose,

    J. Scott, B. Ravichandran, C. Funk, R. T. Collins, and Y . Liu, “From image to stability: Learning dynamics from human pose,” inEuropean conference on computer vision. Springer, 2020, pp. 536–554

    2020

  70. [70]

    Intelligent carpet: Inferring 3d human pose from tactile signals,

    Y . Luo, Y . Li, M. Foshey, W. Shou, P. Sharma, T. Palacios, A. Torralba, and W. Matusik, “Intelligent carpet: Inferring 3d human pose from tactile signals,” inProceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2021, pp. 11 255–11 265

    2021

  71. [71]

    Leveraging rgb-pressure for whole- body human-to-humanoid motion imitation,

    Y . Lu, S. Ren, Q. Shen, and X. Cao, “Leveraging rgb-pressure for whole- body human-to-humanoid motion imitation,” inProceedings of the 32nd ACM International Conference on Multimedia, 2024, pp. 8932–8941

    2024

  72. [72]

    Prox- imal policy optimization algorithms,

    J. Schulman, F. Wolski, P. Dhariwal, A. Radford, and O. Klimov, “Prox- imal policy optimization algorithms,”arXiv preprint arXiv:1707.06347, 2017

    Pith/arXiv arXiv 2017

  73. [73]

    Retargeting matters: General motion retargeting for humanoid motion tracking,

    J. P. Araujo, Y . Ze, P. Xu, J. Wu, and C. K. Liu, “Retargeting matters: General motion retargeting for humanoid motion tracking,” arXiv preprint arXiv:2510.02252, 2025

    arXiv 2025

  74. [74]

    Make tracking easy: Neural motion retargeting for humanoid whole-body control,

    Q. Zhao, K. Yang, X. Wang, S. Zhao, Y . Lu, X. Zhang, Q. Shen, X.-X. Long, and X. Cao, “Make tracking easy: Neural motion retargeting for humanoid whole-body control,”arXiv preprint arXiv:2603.22201, 2026

    Pith/arXiv arXiv 2026

  75. [75]

    Smpl: A skinned multi-person linear model,

    M. Loper, N. Mahmood, J. Romero, G. Pons-Moll, and M. J. Black, “Smpl: A skinned multi-person linear model,” inSeminal Graphics Papers: Pushing the Boundaries, V olume 2, 2023, pp. 851–866

    2023

  76. [76]

    Amass: Archive of motion capture as surface shapes,

    N. Mahmood, N. Ghorbani, N. F. Troje, G. Pons-Moll, and M. J. Black, “Amass: Archive of motion capture as surface shapes,” inProceedings of the IEEE/CVF international conference on computer vision, 2019, pp. 5442–5451

    2019

  77. [77]

    Smpler-x: Scaling up expressive human pose and shape estimation,

    Z. Cai, W. Yin, A. Zeng, C. Wei, Q. Sun, W. Yanjun, H. E. Pang, H. Mei, M. Zhang, L. Zhanget al., “Smpler-x: Scaling up expressive human pose and shape estimation,”Advances in Neural Information Processing Systems, vol. 36, pp. 11 454–11 468, 2023

    2023

  78. [78]

    Physpt: Physics-aware pretrained transformer for estimating human dynamics from monocular videos,

    Y . Zhang, J. O. Kephart, Z. Cui, and Q. Ji, “Physpt: Physics-aware pretrained transformer for estimating human dynamics from monocular videos,” inProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024, pp. 2305–2317. Yi Luis a graduate student for Ph.D degree at the School of Electronic Science and Engineering, Nan- jing ...

    2024