# Realistic Full-Body Tracking from Sparse Observations via Joint-Level Modeling

arXiv: https://arxiv.org/abs/2308.08855 · HTML: https://mlsanity.com/paper/2308.08855/

## Key facts

- Cited by 43 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 48 references that are in the map.
- First posted on arXiv 17 Aug 2023.

## Builds on (most cited first, 25 of 25)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Auto-Encoding Variational Bayes](https://mlsanity.com/paper/1312.6114/) (2013)
- [Expressive Body Capture: 3D Hands, Face, and Body from a Single Image](https://mlsanity.com/paper/1904.05866/) (2019)
- [AMASS: Archive of Motion Capture as Surface Shapes](https://mlsanity.com/paper/1904.03278/) (2019)
- [On the Continuity of Rotation Representations in Neural Networks](https://mlsanity.com/paper/1812.07035/) (2018)
- [Human Motion Diffusion Model](https://mlsanity.com/paper/2209.14916/) (2022)
- [End-to-End Human Pose and Mesh Reconstruction with Transformers](https://mlsanity.com/paper/2012.09760/) (2020)
- [PhysDiff: Physics-Guided Human Motion Diffusion Model](https://mlsanity.com/paper/2212.02500/) (2022)
- [HuMoR: 3D Human Motion Model for Robust Pose Estimation](https://mlsanity.com/paper/2105.04668/) (2021)
- [3D Human Pose Estimation with Spatial and Temporal Transformers](https://mlsanity.com/paper/2103.10455/) (2021)
- [Mesh Graphormer](https://mlsanity.com/paper/2104.00272/) (2021)
- [MixSTE: Seq2seq Mixed Spatio-Temporal Encoder for 3D Human Pose Estimation in Video](https://mlsanity.com/paper/2203.00859/) (2022)
- [Probabilistic Modeling for Human Mesh Recovery](https://mlsanity.com/paper/2108.11944/) (2021)
- [MHFormer: Multi-Hypothesis Transformer for 3D Human Pose Estimation](https://mlsanity.com/paper/2111.12707/) (2021)
- [Physical Inertial Poser (PIP): Physics-aware Real-time Human Motion Tracking from Sparse Inertial Sensors](https://mlsanity.com/paper/2203.08528/) (2022)
- [A Spatio-temporal Transformer for 3D Human Motion Prediction](https://mlsanity.com/paper/2004.08692/) (2020)
- [Epipolar Transformers](https://mlsanity.com/paper/2005.04551/) (2020)
- [AvatarPoser: Articulated Full-Body Pose Tracking from Sparse Motion Sensing](https://mlsanity.com/paper/2207.13784/) (2022)
- [Sparse Inertial Poser: Automatic 3D Human Pose Estimation from Sparse IMUs](https://mlsanity.com/paper/1703.08014/) (2017)
- [QuestSim: Human Motion Tracking from Sparse Sensors with Simulated Avatars](https://mlsanity.com/paper/2209.09391/) (2022)
- [FLAG: Flow-based 3D Avatar Generation from Sparse Observations](https://mlsanity.com/paper/2203.05789/) (2022)
- [LoBSTr: Real-time Lower-body Pose Prediction from Sparse Upper-body Tracking Signals](https://mlsanity.com/paper/2103.01500/) (2021)
- [PPT: token-Pruned Pose Transformer for monocular and multi-view human pose estimation](https://mlsanity.com/paper/2209.08194/) (2022)
- [Learning to Fit Morphable Models](https://mlsanity.com/paper/2111.14824/) (2021)

## Built on by (most cited first, 30 of 43)

- [MaskedMimic: Unified Physics-Based Character Control Through Masked Motion Inpainting](https://mlsanity.com/paper/2409.14393/) (2024)
- [EgoLM: Multi-Modal Language Model of Egocentric Motions](https://mlsanity.com/paper/2409.18127/) (2024)
- [HMD^2: Environment-aware Motion Generation from Single Egocentric Head-Mounted Device](https://mlsanity.com/paper/2409.13426/) (2024)
- [HMD-Poser: On-Device Real-time Human Motion Tracking from Scalable Sparse Observations](https://mlsanity.com/paper/2403.03561/) (2024)
- [Stratified Avatar Generation from Sparse Observations](https://mlsanity.com/paper/2405.20786/) (2024)
- [MultiPhys: Multi-Person Physics-aware 3D Motion Estimation](https://mlsanity.com/paper/2404.11987/) (2024)
- [Ultra Inertial Poser: Scalable Motion Capture and Tracking from Sparse Inertial Sensors and Ultra-Wideband Ranging](https://mlsanity.com/paper/2404.19541/) (2024)
- [A Unified Diffusion Framework for Scene-aware Human Motion Estimation from Sparse Signals](https://mlsanity.com/paper/2404.04890/) (2024)
- [EMHI: A Multimodal Egocentric Human Motion Dataset with HMD and Body-Worn IMUs](https://mlsanity.com/paper/2408.17168/) (2024)
- [EnvPoser: Environment-aware Realistic Human Motion Estimation from Sparse Observations with Uncertainty Modeling](https://mlsanity.com/paper/2412.10235/) (2024)
- [From Sparse Signal to Smooth Motion: Real-Time Motion Generation with Rolling Prediction Models](https://mlsanity.com/paper/2504.05265/) (2025)
- [Estimating Ego-Body Pose from Doubly Sparse Egocentric Video Data](https://mlsanity.com/paper/2411.03561/) (2024)
- [Transformer IMU Calibrator: Dynamic On-body IMU Calibration for Inertial Motion Capture](https://mlsanity.com/paper/2506.10580/) (2025)
- [EventEgo3D++: 3D Human Motion Capture from a Head-Mounted Event Camera](https://mlsanity.com/paper/2502.07869/) (2025)
- [mmDEAR: mmWave Point Cloud Density Enhancement for Accurate Human Body Reconstruction](https://mlsanity.com/paper/2503.02375/) (2025)
- [Human Motion Capture from Loose and Sparse Inertial Sensors with Garment-aware Diffusion Models](https://mlsanity.com/paper/2506.15290/) (2025)
- [ECHO: Ego-Centric modeling of Human-Object interactions](https://mlsanity.com/paper/2508.21556/) (2025)
- [DragPoser: Motion Reconstruction from Variable Sparse Tracking Signals via Latent Space Optimization](https://mlsanity.com/paper/2406.14567/) (2024)
- [XR-MBT: Multi-modal Full Body Tracking for XR through Self-Supervision with Learned Depth Point Cloud Registration](https://mlsanity.com/paper/2411.18377/) (2024)
- [Ground Reaction Inertial Poser: Physics-based Human Motion Capture from Sparse IMUs and Insole Pressure Sensors](https://mlsanity.com/paper/2603.16233/) (2026)
- [Semantics-aware Test-time Adaptation for 3D Human Pose Estimation](https://mlsanity.com/paper/2502.10724/) (2025)
- [SSD-Poser: Avatar Pose Estimation with State Space Duality from Sparse Observations](https://mlsanity.com/paper/2504.18332/) (2025)
- [KineST: A Kinematics-guided Spatiotemporal State Space Model for Human Motion Tracking from Sparse Signals](https://mlsanity.com/paper/2512.16791/) (2025)
- [Egocentric Visibility-Aware Human Pose Estimation](https://mlsanity.com/paper/2602.23618/) (2026)
- [A Two-Stage Motion-Aware Framework for mmWave-based Human Mesh Recovery](https://mlsanity.com/paper/2605.08530/) (2026)
- [EgoExoMoCap: Distributed Ego-Exo Human Motion Capture](https://mlsanity.com/paper/2607.15868/) (2026)
- [Social EgoMesh Estimation](https://mlsanity.com/paper/2411.04598/) (2024)
- [Efficient 3D Full-Body Motion Generation from Sparse Tracking Inputs with Temporal Windows](https://mlsanity.com/paper/2505.01802/) (2025)
- [MAGE:A Multi-stage Avatar Generator with Sparse Observations](https://mlsanity.com/paper/2505.06411/) (2025)
- [Cognitive State Inference from VR Motion via Motion Foundation Model](https://mlsanity.com/paper/2509.24255/) (2025)

## Abstract (arXiv)

To bridge the physical and virtual worlds for rapidly developed VR/AR applications, the ability to realistically drive 3D full-body avatars is of great significance. Although real-time body tracking with only the head-mounted displays (HMDs) and hand controllers is heavily under-constrained, a carefully designed end-to-end neural network is of great potential to solve the problem by learning from large-scale motion data. To this end, we propose a two-stage framework that can obtain accurate and smooth full-body motions with the three tracking signals of head and hands only. Our framework explicitly models the joint-level features in the first stage and utilizes them as spatiotemporal tokens for alternating spatial and temporal transformer blocks to capture joint-level correlations in the second stage. Furthermore, we design a set of loss terms to constrain the task of a high degree of freedom, such that we can exploit the potential of our joint-level modeling. With extensive experiments on the AMASS motion dataset and real-captured data, we validate the effectiveness of our designs and show our proposed method can achieve more accurate and smooth motion compared to existing approaches.