IP Library › Granted Patent US 12,482,188
Granted Patent B2
US 12,482,188 · App. 18/742,054 · Granted Nov 25, 2025

Simulated control for 3-dimensional human poses in virtual reality environments

Inventors: Jason Saragih (Pittsburgh, PA); Shih-En Wei (Pittsburgh, PA); Tomas Simon Kreuz (Pittsburgh, PA); Kris Makoto Kitani (Pittsburgh, PA); Ye Yuan (Pittsburgh, PA)
Assignee: Meta Platforms Technologies, LLC
G06T19/00G06T15/10G06V40/103G06V40/23
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,482,188
App. No.
18/742,054
Granted
Nov 25, 2025
Kind
B2
Abstract

A method for simulating a solid body animation of a subject includes retrieving a first frame that includes a body image of a subject. The method also includes selecting, from the first frame, multiple key points within the body image of the subject that define a hull of a body part and multiple joint points that define a joint between two body parts, identifying a geometry, a speed, and a mass of the body part to include in a dynamic model of the subject, based on the key points and the joint points, determining, based on the dynamic model of the subject, a pose of the subject in a second frame after the first frame in a video stream, and providing the video stream to an immersive reality application running on a client device.

Claims (50)

1 . A computer-implemented method, comprising:

retrieving frames in a video stream including a subject;

selecting, from the frames, multiple key points within a body of the subject that define a hull of a body part and multiple joint points that define a joint between two body parts;

identifying geometric constraints of the body part based at least on the hull, the multiple key points, and the joint points;

generating a dynamic model of the subject based on the geometric constraints; determining, based on the dynamic model of the subject, a first pose of the subject in the frames;

identifying an action for the dynamic model of the subject based on the first pose and the key points;

estimating, based on the action, a second pose of the subject in a next frame in the video stream; and

providing the second pose based on the video stream to an immersive reality application running on a client device.

2 . The computer-implemented method of claim 1 , further comprising forming a first frame, included in the frames in the video stream, with the dynamic model of the subject.

3 . The computer-implemented method of claim 1 , further comprising determining a gradient factor to associate the second pose of the subject with a transition dynamics rule, based on a previous pose of the subject, a previous action feature, and an action policy in the dynamic model of the subject.

4 . The computer-implemented method of claim 1 , wherein

estimating a second pose of the subject comprises determining a gradient factor to obtain a position for each joint point and each key point in the second pose of the subject, based on the action and an action policy in the dynamic model of the subject.

5 . The computer-implemented method of claim 1 , wherein

estimating a second pose of the subject comprises associating a torque field acting on each of the joint points based on the geometric constraints, a speed of the body part based on a first frame and second frame in the frames, and a mass of the body part.

6 . The computer-implemented method of claim 4 , further comprising determining the action that causes the subject to move based on the geometric constraints, the speed, and the mass of the body part.

7 . The computer-implemented method of claim 1 , wherein

estimating a second pose of the subject comprises identifying physical constraints for the body of the subject relative to an environment in the video stream in the next frame.

8 . The computer-implemented method of claim 1 , wherein

the dynamic model of the subject comprises a physics simulation tool to determine a state of the subject and an action policy tool that determines the action causally associated with the state of the subject, further comprising updating the physics simulation tool faster than the action policy tool.

9 . The computer-implemented method of claim 1 , further comprising

identifying the geometric constraints, a speed, and a mass of the body part by correlating the key points and the joint points between a first frame and the next frame, based on a time elapsed between the first frame and the next frame in the video stream.

10 . The computer-implemented method of claim 1 , wherein

providing the video stream to an immersive reality application comprises selecting a view point of the subject based on the immersive reality application.

11 . A system, comprising:

a memory storing multiple instructions; and

one or more processors configured to execute the instructions to cause the system to perform operations, comprising:

retrieving frames in a video stream including a subject;

selecting, from the frames, multiple key points within a body of the subject that define a hull of a body part and multiple joint points that define a joint between two body parts;

identifying geometric constraints of the body part based at least on the hull, the multiple key points, and the joint points;

generating a dynamic model of the subject based on the geometric constraints; determining, based on the dynamic model of the subject, a first pose of the subject in the frames;

identifying an action for the dynamic model of the subject based on the first pose and the key points in the frames;

estimating, based on the action, a second pose of the subject in a next frame in the video stream; and

providing the second pose based on the video stream to an immersive reality application running on a client device.

12 . The system of claim 11 , wherein the one or more processors execute instructions to form a first frame, included in the frames of the video stream, with the dynamic model of the subject.

13 . The system of claim 11 , wherein the one or more processors further execute instructions to determine a gradient factor to associate the second pose of the subject with a transition dynamics rule, based on a previous pose of the subject, a previous action feature, and an action policy in the dynamic model of the subject.

14 . The system of claim 11 , wherein to estimate the second pose of the subject the one or more processors execute instructions to determine a gradient factor to obtain a position for each joint point and each key point in the second pose of the subject, based on the action and an action policy in the dynamic model of the subject.

15 . A computer-implemented method for training a model to simulate a solid body human pose, comprising:

retrieving multiple frames of a subject in a video stream;

for the frames, selecting multiple key points within a body of the subject that define a hull of a body part and multiple joint points that define a joint between two body parts;

identifying a first position of the subject based on the key points and the joint points;

identifying an action for a dynamic model of the subject based on the first position and the key points;

generating a next position for each joint point and each key point based on the dynamic model of the subject, the first position, and the action that causes the subject to move;

determining a difference between the next position for each joint point and each key point and a ground truth position for each key point and each joint point extracted from at least one of the frames in the video stream;

updating the dynamic model of the subject based on the difference, wherein an updated next position is determined based on the updated dynamic model; and

storing the dynamic model of the subject in a memory circuit.

16 . The computer-implemented method of claim 15 , further comprising: determining a confidence level for the multiple key points; and determining a difference comprises factoring the confidence level for each of the key points in the difference.

17 . The computer-implemented method of claim 15 , further comprising providing the dynamic model of the subject to a client device for an immersive reality application.

18 . The computer-implemented method of claim 15 , wherein updating the dynamic model of the subject comprises adding a residual force and torque to the action that causes the subject to move.

19 . The computer-implemented method of claim 15 , further comprising defining a kinematics policy based on a Gaussian distribution for features around mean values, and updating the dynamic model of the subject comprises using a covariance from the Gaussian distribution to update the dynamic model of the subject.

20 . The computer-implemented method of claim 15 , wherein updating the dynamic model of the subject further comprises adjusting an action policy in the dynamic model of the subject to increase a reward value based on an accuracy of a position, an orientation, and a speed of the body part of the subject at a time corresponding to a first frame in the video stream.

Assignments (2)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jun 28, 2024
From: SARAGIH, JASON; WEI, SHIH-EN; SIMON KREUZ, TOMAS; KITANI, KRIS MAKOTO; YUAN, YE
To: FACEBOOK TECHNOLOGIES, LLC
Reel/Frame 067867/0612 →
CHANGE OF NAME Recorded Jun 28, 2024
From: FACEBOOK TECHNOLOGIES, LLC
To: META PLATFORMS TECHNOLOGIES, LLC
Reel/Frame 067964/0665 →
Continuity (3)
Continuation 17556429 · Dec 20, 2021
Provisional Application 63130005 · Dec 23, 2020
Related Publication 20240346770A1 · Oct 17, 2024
References Cited (99)
US 8531464B1 · Cohen Bengio · 2013 [cited by examiner]
US 11055891B1 · Ofek · 2021 [cited by examiner]
US 12056824B2 · Saragih et al. · 2024 [cited by applicant]
US 20120328158A1 · Lefevre · 2012 [cited by examiner]
US 20130321398A1 · Howard · 2013 [cited by examiner]
US 20140369595A1 · Pavlidis · 2014 [cited by examiner]
US 20150106052A1 · Balakrishnan et al. · 2015 [cited by applicant]
US 20180110398A1 · Schwartz · 2018 [cited by examiner]
US 20200250874A1 · Assouline et al. · 2020 [cited by applicant]
US 20200364901A1 · Choudhuri · 2020 [cited by examiner]
US 20220035443A1 · Winold et al. · 2022 [cited by applicant]
US 20220083125A1 · Lefaudeux et al. · 2022 [cited by applicant]
US 20220207831A1 · Saragih · 2022 [cited by examiner]
US 20240241573A1 · Peris et al. · 2024 [cited by applicant]
US 20240331250A1 · Bazin et al. · 2024 [cited by applicant]
TW 201727439A · 2017 [cited by applicant]
Rempe D., et al., “Contact and Human Dynamics from Monocular Video,” In Proceedings of the European Conference on Computer Vision (ECCV), 2020, pp. 1-27. [cited by applicant]
Schulman J., et al., “High-Dimensional Continuous Control Using Generalized Advantage Estimation,” arXiv preprint arXiv:1506.02438, 2015, pp. 1-14. [cited by applicant]
Schulman J., et al., “Proximal Policy Optimization Algorithms,” Machine Learning, arXiv preprint arXiv:1707.06347, 2017, pp. 1-12. [cited by applicant]
Shimada S., et al., “Physcap: Physically Plausible Monocular 3D Motion Capture in Real Time,” ACM Transactions on Graphics (TOG), Dec. 2020, vol. 39, No. 6, 16 pages. [cited by applicant]
Song J., et al., “Human Body Model Fitting by Learned Gradient Descent,” In Proceedings of the European Conference on Computer Vision (ECCV), 2020, pp. 1-17. [cited by applicant]
Sun Y., et al., “Human Mesh Recovery from Monocular Images via a Skeleton-Disentangled Representation,” In Proceedings of the IEEE International Conference on Computer Vision (CCV), 2019, pp. 5349-5358. [cited by applicant]
Tan J.K.V., et al., “Indirect Deep Structured Learning for 3D Human Body Shape and Pose Prediction,” British Machine Vision Conference (BMVC), 2017, pp. 1-11. [cited by applicant]
Todorov E., et al., “MuJoCo: A Physics Engine for Model-Based Control,” In 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems (IRS), 2012, pp. 5026-5033. [cited by applicant]
Tung H., et al., “Self-supervised Learning of Motion Capture,” 31st Conference on Neural Information Processing Systems (NIPS 2017), arXiv: 1712.01337v1 [cs.CV], Dec. 4, 2013, Long Beach, CA, pp. 1-11. [cited by applicant]
Vaswani A., et al., “Attention Is All You Need,” Advances in Neural Information Processing Systems, December (NIPS), Dec. 4, 2017, pp. 5998-6008. [cited by applicant]
Vondrak M., et al., “Video-Based 3D Motion Capture Through Biped Control,” ACM Transactions On Graphics (TOG), 2012, vol. 31, No. 4, pp. 1-12. [cited by applicant]
Wang Z., et al., “Robust Imitation of Diverse Behaviors,” In Advances in Neural Information Processing Systems (NIPS), 2017, pp. 5320-5329. [cited by applicant]
Wei S.E., et al., “Convolutional Pose Machines,” The Conference on Computer Vision and Pattern Recognition (CVPR), 2016, pp. 4724-4732. [cited by applicant]
Wei X., et al., “VideoMocap: Modeling Physically Realistic Human Motion from Monocular Video Sequences,” In Acm Siggraph 2010 papers, 2010, vol. 29, No. 4, Article 42, pp. 1-10. [cited by applicant]
Won J., et al., “A Scalable Approach to Control Diverse Behaviors for Physically Simulated Characters,” ACM Transactions on Graphics (TOG), 2020, vol. 39, No. 4, Article 33, pp. 1-12. [cited by applicant]
Xiang D., et al., “Monocular Total Capture: Posing Face, Body, and Hands in the Wild,” In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019, pp 10965-10974. [cited by applicant]
Yuan Y., et al., “3D Ego-Pose Estimation via Imitation Learning,” Proceedings of European Conference on Computer Vision (ECCV), 2018, pp. 1-16. [cited by applicant]
Yuan Y., et al., “Ego-Pose Estimation and Forecasting as Real-Time PD Control,” International Conference on Computer Vision (ICCV), 2019, pp. 10082-10092. [cited by applicant]
Yuan Y., et al., “Residual Force Control for Agile Human Behavior Imitation and Extended Motion Synthesis,” In Advances in Neural Information Processing Systems (NIPS), 2020, pp. 1-12. [cited by applicant]
Yuan Y., et al., “SimPoE: Simulated Character Control for 3D Human Pose Estimation,” Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021, 6 pages. [cited by applicant]
Zell P., et al., “Joint 3D Human Motion Capture and Physical Analysis from Monocular Videos,” In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops(CVPR), 2017, pp. 17-26. [cited by applicant]
Amberg B., et al., “Optimal Step Nonrigid ICP Algorithms for Surface Registration,” In 2007 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2007, pp. 1-8. [cited by applicant]
Anguelov D., et al., “Scape: Shape Completion and Animation of People,” In ACM SIGGRAPH 2005 Papers, 2005, pp. 408-416. [cited by applicant]
Arnab A., et al., “Exploiting Temporal Context for 3D Human Pose Estimation in the Wild,” In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2019, pp. 3395-3404. [cited by applicant]
Bergamin K., et al., “DReCon: Data-Driven Responsive Control of Physics-Based Characters,” ACM Transactions on Graphics (TOG), Nov. 2019, vol. 38, No. 6, pp. 1-11. [cited by applicant]
Bogo F., et al., “Keep It SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Image,” In European Conference on Computer Vision (ECCV), Springer, 2016, pp. 561-578. [cited by applicant]
Brubaker M.A., et al., “Estimating Contact Dynamics,” In 2009 IEEE 12th International Conference on Computer Vision (ICCV), 2009, pp. 2389-2396. [cited by applicant]
Cao Z., et al., “Realtime Multi-Person 2D Pose Estimation Using Part Affinity Fields,” In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017, pp. 7291-7299. [cited by applicant]
Dabral R., et al., “Learning 3D Human Pose from Structure and Motion,” In Proceedings of the European Conference on Computer Vision (ECCV), 2018, pp. 668-683. [cited by applicant]
Erwin Coumans: “Bullet Physics Engine,” Open Source Software, 2010, 1(3):84, Retrieved from the Internet: URL: http://bulletphysics.org, 40 pages. [cited by applicant]
Gong W., et al., “Human Pose Estimation from Monocular Images: A Comprehensive Survey,” Sensors, Nov. 25, 2016, vol. 16, No. 12, pp. 1-39. [cited by applicant]
Guler R.A., et al., “HoloPose: Holistic 3D Human Reconstruction In-The-Wild,” In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019, pp. 10884-10894. [cited by applicant]
He; et al., “Deep Residual Learning for Image Recognition,” In Proceedings of The IEEE Conference on Computer Vision and Pattern Recognition, Jun. 27-30, 2016, pp. 770-778. [cited by applicant]
Ho J., et al., “Generative Adversarial Imitation Learning,” In Advances in Neural Information Processing Systems (NIPS), 2016, 9 pages. [cited by applicant]
Hossain M.R.I., et al., “Exploiting Temporal Information for 3D Human Pose Estimation,” In Proceedings of the European Conference on Computer Vision (ECCV), 2018, pp. 68-84. [cited by applicant]
Hoyet L., et al., “Push it Real: Perceiving Causality in Virtual Interactions,” ACM Transactions on Graphics (TOG), Jul. 2012, vol. 31, No. 4, pp. 1-9. [cited by applicant]
Huang Y., et al., “Towards Accurate Marker-Less Human Shape and Pose Estimation over Time,” In 2017 International Conference on 3D vision (3DV), IEEE, 2017, pp. 421-430. [cited by applicant]
International Preliminary Report on Patentability for International Application No. PCT/US2021/064860, mailed Jul. 6, 2023, 7 pages. [cited by applicant]
International Search Report and Written Opinion for International Application No. PCT/US2021/064860, mailed Apr. 4, 2022, 8 pages. [cited by applicant]
Ionescu C., et al., “Human3.6M: Large Scale Datasets and Predictive Methods for 3D Human Sensing in Natural Environments,” IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013, vol. 36, No. 7, pp. 1325-1… [cited by applicant]
Isogawa M., et al., “Optical Non-Line-of-Sight Physics-Based 3D Human Pose Estimation,” In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020, pp. 7013-7022. [cited by applicant]
Kanazawa A., et al., “End-to-end Recovery of Human Shape and Pose,” Computer Vision and Pattern Recognition (CVPR), Jun. 2018, pp. 7122-7131. [cited by applicant]
Kanazawa; et al., “Learning 3D Human Dynamics from Video,” In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Jun. 2019, pp. 5614-5623. [cited by applicant]
Kavan L., et al., “Skinning with Dual Quaternions,” In Proceedings of the 2007 Symposium on Interactive 3D Graphics and Games, 2007, pp. 39-46. [cited by applicant]
Kingma; et al., “ADAM: A Method for Stochastic Optimization,” ArXir:1412.6980v1, Dec. 22, 2014, 9 pages. [cited by applicant]
Kocabas M., et al., “VIBE: Video Inference for Human Body Pose and Shape Estimation,” In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020, pp. 5253-5263. [cited by applicant]
Kolotouros N., et al., “Learning to Reconstruct 3D Human Pose and Shape via Model-Fitting in the Loop,” In Proceedings of the IEEE International Conference on Computer Vision (CCV), 2019, pp. 2252-2261. [cited by applicant]
Lassner C., et al., “Unite the People: Closing the Loop Between 3D and 2D Human Representations,” In Proceedings of the IEEE Computer Vision and Pattern Recognition (CVPR), Jan. 10, 2017, pp. 6050-6059. [cited by applicant]
Li Z., et al., “Estimating 3D Motion and Forces of Person-Object Interactions from Monocular Video,” In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019, pp. 8640-8649. [cited by applicant]
Liu L., et al., “Learning Basketball Dribbling Skills using Trajectory Optimization and Deep Reinforcement Learning,” ACM Transactions on Graphics (TOG), 2018, vol. 37, No. 4, pp. 1-14. [cited by applicant]
Liu L., et al., “Learning to Schedule Control Fragments for Physics-Based Characters Using Deep Q-Learning,” ACM Transactions on Graphics (TOG), Jun. 2017, vol. 36, No. 3, Article 29, pp. 1-14. [cited by applicant]
Loper M., et al., “SMPL: A Skinned Multi-Person Linear Model,” ACM Transactions on Graphics, Nov. 2015, vol. 34 (6), pp. 248:1-248:16. [cited by applicant]
Luo Z., et al., “3D Human Motion Estimation via Motion Compression and Refinement,” Proceedings of the Asian Conference on Computer Vision (ACCV), 2020, pp. 1-17. [cited by applicant]
Makris A., et al., “Robust 3D Human Pose Estimation Guided by Filtered Subsets of Body Keypoints,” 16th International Conference On Machine Vision Applications (MVA), May 27, 2019, pp. 1-6. [cited by applicant]
Mehta D., et al., “Single-Shot Multi-Person 3D Pose Estimation from Monocular RGB,” In 2018 International Conference on 3D Vision (3DV), IEEE, 2018, pp. 120-130. [cited by applicant]
Mehta; et al., “VNect: Real-Time 3D Human Pose Estimation with a Single RGB Camera,” ACM Transactions on Graphics (TOG), Jul. 20, 2017, vol. 36, pp. 1-14. [cited by applicant]
Merel J., et al., “Catch Carry: Reusable Neural Controllers for Vision-Guided Whole-Body Tasks,” ACM Transactions on Graphics (TOG), Jul. 2020, vol. 39, No. 4, Article 39, pp. 1-14. [cited by applicant]
Merel J., et al., “Hierarchical Visuomotor Control of Humanoids,” arXiv preprint arXiv:1811.09656, 2018, pp. 1-18. [cited by applicant]
Merel J., et al., “Learning Human Behaviors from Motion Capture by Adversarial Imitation,” arXiv preprint arXiv:1707.02201, 2017, pp. 1-12. [cited by applicant]
Merel J., et al., “Neural Probabilistic Motor Primitives for Humanoid Control,” arXiv preprint arXiv:1811.11711, 2018, pp. 1-14. [cited by applicant]
Moon G., et al., “I2L-MeshNet: Image-to-Lixel Prediction Network for Accurate 3D Human Pose and Mesh Estimation from a Single RGB Image,” In European Conference on Computer Vision (ECCV), 2020, pp. 1-23. [cited by applicant]
Omranl, et al., “Neural Body Fitting: Unifying Deep Learning and Model-Based Human Pose and Shape Estimation,” arXiv: 18n8.05942v1 [cs.CV], Aug. 17, 2018, pp. 484-494. [cited by applicant]
Park S., et al., “Learning Predict-And-Simulate Policies from Unorganized Human Motion Data,” ACM Transactions on Graphics (TOG), 2019, vol. 38, No. 6, pp. 1-11. [cited by applicant]
Pavlakos G., et al., “Expressive Body Capture: 3D Hands, Face, and Body from a Single Image,” In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019, pp. 10975-10985. [cited by applicant]
Pavlakos G., et al., “Learning to Estimate 3D Human Pose and Shape from a Single Color Image,” In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018, pp. 459-468. [cited by applicant]
Pavllo D., et al., “3D Human Pose Estimation in Video with Temporal Convolutions and Semi-Supervised Training,” In Proceedings of Computer Vision and Pattern Recognition (CVPR), 2019, pp. 7753-7762. [cited by applicant]
Peng X.B., et al., “Deep Mimic: Example-Guided Deep Reinforcement Learning of Physics-Based Character Skills,” ACM Transactions on Graphics, Aug. 2018, vol. 37 (4), Article 143, pp. 143:1-143:18. [cited by applicant]
Peng X.B., et al., “SFV: Reinforcement Learning of Physical Skills from Videos,” ACM Transactions on Graphics, Nov. 2018, vol. 37, No. 6, Article 178, 17 pages, Retrieved from the Internet: URL: https://doi.org/10.1145/… [cited by applicant]
Peng X.B., et al., “Learning Locomotion Skills Using DeepRL: Does the Choice of Action Space Matter?,” In Proceedings of the ACM SIGGRAPH/Eurographics Symposium on Computer Animation, 2017, pp. 1-13. [cited by applicant]
Peng X.B., et al., “MCP: Learning Composable Hierarchical Control with Multiplicative Compositional Policies,” In Advances in Neural Information Processing Systems (NIPS), 2019, pp. 3681-3692. [cited by applicant]
REITSMA P.S.A., et al., “Perceptual Metrics for Character Animation: Sensitivity to Errors in Ballistic Motion,” In ACM SIGGRAPH 2003 Papers, 2003, pp. 537-542. [cited by applicant]
Office Action mailed Feb. 26, 2025 for Taiwan Application No. 110148341, filed Dec. 23, 2021, 8 pages. [cited by applicant]
Extended European Search Report for European Patent Application No. 24155497.1, mailed Nov. 5, 2024, 12 pages. [cited by applicant]
International Preliminary Report on Patentability for International Application No. PCT/US2024/011606, mailed Jul. 24, 2025, 8 pages. [cited by applicant]
International Search Report and Written Opinion for International Application No. PCT/US2024/011606, mailed Apr. 2, 2024, 11 pages. [cited by applicant]
Ponton J. L., et al., “Combining Motion Matching and Orientation Prediction to Animate Avatars for Consumer-grade VR Devices,” Computer Graphics Forum, 2022, vol. 41, No. 8, pp. 107-118. [cited by applicant]
Pustka D., et al., “Optical Outside-in Tracking Using Unmodified Mobile Phones,” IEEE International Symposium on Mixed and Augmented Reality, Nov. 5, 2012, pp. 81-89. [cited by applicant]
Villegas R., et al., “Neural Kinematic Networks for Unsupervised Motion Retargetting,” Proceedings of the IEEE conference on computer vision and pattern recognition, Jun. 18, 2018, pp. 8639-8648. [cited by applicant]
Winkler A., et al., “QuestSim: Human Motion Tracking from Sparse Sensors with Simulated Avatars,” SIGGRAPH Asia 2022 Conference Papers, Nov. 29, 2022, 8 pages. [cited by applicant]
Yang D., et al., “Lobstr: Real-time Lower-body Pose Prediction from Sparse Upper-body Tracking Signals,” Computer Graphics Forum, Jun. 4, 2021, vol. 40, No. 2, pp. 265-275. [cited by applicant]
Yuan Y., et al., “PhysDiff: Physics-Guided Human Motion Diffusion Model,” arXiv:2212.02500v1, Dec. 5, 2022, 13 pages. [cited by applicant]
Anonymous., “HTC Vive,” Wikipedia, Mar. 28, 2023, [Retrieved on Aug. 3, 2024], 7 Pages, Retrieved from the Internet URL: https://en.wikipedia.org/w/index.php?title=HTCVive&oldid=1146984052. [cited by applicant]
Anonymous., “Just Lower Body Tracking?—Driver4VR—Enhance Your VR,” Jun. 5, 2020, [Retrieved on Aug. 3, 2024], 3 Pages, Retrieved from the Internet URL: https://www.driver4vr.com/forums/topic/just-lower-body-tracking/. [cited by applicant]