# Dyn-HaMR: Recovering 4D Interacting Hand Motion from a Dynamic Camera

arXiv: https://arxiv.org/abs/2412.12861 · HTML: https://mlsanity.com/paper/2412.12861/

## Key facts

- Cited by 51 papers in the map (data through 14 Oct 2026).
- Builds on 44 of its 59 references that are in the map.
- First posted on arXiv 17 Dec 2024.

## Builds on (most cited first, 30 of 44)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D Cameras](https://mlsanity.com/paper/2108.10869/) (2021)
- [MediaPipe: A Framework for Building Perception Pipelines](https://mlsanity.com/paper/1906.08172/) (2019)
- [Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives](https://mlsanity.com/paper/2311.18259/) (2023)
- [HOI4D: A 4D Egocentric Dataset for Category-Level Human-Object Interaction](https://mlsanity.com/paper/2203.01577/) (2022)
- [HuMoR: 3D Human Motion Model for Robust Pose Estimation](https://mlsanity.com/paper/2105.04668/) (2021)
- [ARCTIC: A Dataset for Dexterous Bimanual Hand-Object Manipulation](https://mlsanity.com/paper/2204.13662/) (2022)
- [Reconstructing Hands in 3D with Transformers](https://mlsanity.com/paper/2312.05251/) (2023)
- [H2O: Two Hands Manipulating Objects for First Person Interaction Recognition](https://mlsanity.com/paper/2104.11181/) (2021)
- [InterHand2.6M: A Dataset and Baseline for 3D Interacting Hand Pose Estimation from a Single RGB Image](https://mlsanity.com/paper/2008.09309/) (2020)
- [First-Person Hand Action Benchmark with RGB-D Videos and 3D Hand Pose Annotations](https://mlsanity.com/paper/1704.02463/) (2017)
- [WHAM: Reconstructing World-grounded Humans with Accurate 3D Motion](https://mlsanity.com/paper/2312.07531/) (2023)
- [3D Hand Shape and Pose from Images in the Wild](https://mlsanity.com/paper/1902.03451/) (2019)
- [Deep Patch Visual Odometry](https://mlsanity.com/paper/2208.04726/) (2022)
- [Character Controllers Using Motion VAEs](https://mlsanity.com/paper/2103.14274/) (2021)
- [3D Point Cloud Generative Adversarial Network Based on Tree Structured Graph Convolutions](https://mlsanity.com/paper/1905.06292/) (2019)
- [GLAMR: Global Occlusion-Aware Human Mesh Recovery with Dynamic Cameras](https://mlsanity.com/paper/2112.01524/) (2021)
- [Decoupling Human and Camera Motion from Videos in the Wild](https://mlsanity.com/paper/2302.12827/) (2023)
- [HOT3D: Hand and Object Tracking in 3D from Egocentric Multi-View Videos](https://mlsanity.com/paper/2411.19167/) (2024)
- [End-to-end Hand Mesh Recovery from a Monocular RGB Image](https://mlsanity.com/paper/1902.09305/) (2019)
- [Pushing the Envelope for RGB-based Dense 3D Hand Pose Estimation via Neural Rendering](https://mlsanity.com/paper/1904.04196/) (2019)
- [We are More than Our Joints: Predicting how 3D Bodies Move](https://mlsanity.com/paper/2012.00619/) (2020)
- [Monocular Real-time Hand Shape and Motion Capture using Multi-modal Data](https://mlsanity.com/paper/2003.09572/) (2020)
- [Weakly Supervised 3D Hand Pose Estimation via Biomechanical Constraints](https://mlsanity.com/paper/2003.09282/) (2020)
- [Structured Prediction Helps 3D Human Motion Modelling](https://mlsanity.com/paper/1910.09070/) (2019)
- [Interacting Attention Graph for Single Image Two-Hand Reconstruction](https://mlsanity.com/paper/2203.09364/) (2022)
- [Real-time Hand Tracking under Occlusion from an Egocentric RGB-D Sensor](https://mlsanity.com/paper/1704.02201/) (2017)
- [Context-aware Human Motion Prediction](https://mlsanity.com/paper/1904.03419/) (2019)
- [NeMF: Neural Motion Fields for Kinematic Animation](https://mlsanity.com/paper/2206.03287/) (2022)

## Built on by (most cited first, 30 of 51)

- [Being-H0: Vision-Language-Action Pretraining from Large-Scale Human Videos](https://mlsanity.com/paper/2507.15597/) (2025)
- [Being-H0.5: Scaling Human-Centric Robot Learning for Cross-Embodiment Generalization](https://mlsanity.com/paper/2601.12993/) (2026)
- [Emergence of Human to Robot Transfer in Vision-Language-Action Models](https://mlsanity.com/paper/2512.22414/) (2025)
- [World Models for Learning Dexterous Hand-Object Interactions from Human Videos](https://mlsanity.com/paper/2512.13644/) (2025)
- [Predicting 4D Hand Trajectory from Monocular Videos](https://mlsanity.com/paper/2501.08329/) (2025)
- [MagicHOI: Leveraging 3D Priors for Accurate Hand-object Reconstruction from Short Monocular Video Clips](https://mlsanity.com/paper/2508.05506/) (2025)
- [Hand2World: Autoregressive Egocentric Interaction Generation via Free-Space Hand Gestures](https://mlsanity.com/paper/2602.09600/) (2026)
- [HumanEgo: Zero-Shot Robot Learning from Minutes of Human Egocentric Videos](https://mlsanity.com/paper/2605.24934/) (2026)
- [Dexterous Manipulation Policies from RGB Human Videos via 3D Hand-Object Trajectory Reconstruction](https://mlsanity.com/paper/2602.09013/) (2026)
- [OSMO: Open-Source Tactile Glove for Human-to-Robot Skill Transfer](https://mlsanity.com/paper/2512.08920/) (2025)
- [ACE-Ego-0: Unifying Egocentric Human and Robotic Data for VLA Pretraining](https://mlsanity.com/paper/2606.17200/) (2026)
- [WHOLE: World-Grounded Hand-Object Lifted from Egocentric Videos](https://mlsanity.com/paper/2602.22209/) (2026)
- [EgoGrasp: World-Space Hand-Object Interaction Estimation from Egocentric Videos](https://mlsanity.com/paper/2601.01050/) (2026)
- [Geometric Neural Distance Fields for Learning Human Motion Priors](https://mlsanity.com/paper/2509.09667/) (2025)
- [Learning Dexterous Manipulation Using Contact Wrench Guidance From Human Demonstration](https://mlsanity.com/paper/2607.00033/) (2026)
- [The Surprising Effectiveness of Video Diffusion Models for Hand Motion Reconstruction](https://mlsanity.com/paper/2606.30308/) (2026)
- [AGILE: Hand-Object Interaction Reconstruction from Video via Agentic Generation](https://mlsanity.com/paper/2602.04672/) (2026)
- [Towards Dynamic 3D Reconstruction of Hand-Instrument Interaction in Ophthalmic Surgery](https://mlsanity.com/paper/2505.17677/) (2025)
- [PALM: A Dataset and Baseline for Learning Multi-subject Hand Prior](https://mlsanity.com/paper/2511.05403/) (2025)
- [Efficient and Scalable Monocular Human-Object Interaction Motion Reconstruction](https://mlsanity.com/paper/2512.00960/) (2025)
- [Grasp in Gaussians: Fast Monocular Reconstruction of Dynamic Hand-Object Interactions](https://mlsanity.com/paper/2604.12929/) (2026)
- [EgoForce: Forearm-Guided Camera-Space 3D Hand Pose from a Monocular Egocentric Camera](https://mlsanity.com/paper/2605.12498/) (2026)
- [Open-CHOIR: Open-World Contact-Aware 4D Hand-Object Interaction Reconstruction](https://mlsanity.com/paper/2605.20992/) (2026)
- [ACE-Data-0: Human-Centric Ambient Capture as Embodied Data Engine](https://mlsanity.com/paper/2607.28625/) (2026)
- [UniHand: A Unified Model for Diverse Controlled 4D Hand Motion Modeling](https://mlsanity.com/paper/2602.21631/) (2026)
- [HandX: Scaling Bimanual Motion and Interaction Generation](https://mlsanity.com/paper/2603.28766/) (2026)
- [StableHand: Quality-Aware Flow Matching for World-Space Dual-Hand Motion Estimation from Egocentric Video](https://mlsanity.com/paper/2605.18553/) (2026)
- [HandsOnWorld: Unconstrained Egocentric Video Generation with Camera-Disentangled Hand Control](https://mlsanity.com/paper/2607.02075/) (2026)
- [HandFlow: Fully Generative 4D Hand Recovery with Flow Matching](https://mlsanity.com/paper/2607.11221/) (2026)
- [ACE-Ego-Hand: Repurposing Video Diffusion Models for Occlusion-Robust Egocentric 3D Hand Motion Recovery](https://mlsanity.com/paper/2608.20308/) (2026)

## Abstract (arXiv)

We propose Dyn-HaMR, to the best of our knowledge, the first approach to reconstruct 4D global hand motion from monocular videos recorded by dynamic cameras in the wild. Reconstructing accurate 3D hand meshes from monocular videos is a crucial task for understanding human behaviour, with significant applications in augmented and virtual reality (AR/VR). However, existing methods for monocular hand reconstruction typically rely on a weak perspective camera model, which simulates hand motion within a limited camera frustum. As a result, these approaches struggle to recover the full 3D global trajectory and often produce noisy or incorrect depth estimations, particularly when the video is captured by dynamic or moving cameras, which is common in egocentric scenarios. Our Dyn-HaMR consists of a multi-stage, multi-objective optimization pipeline, that factors in (i) simultaneous localization and mapping (SLAM) to robustly estimate relative camera motion, (ii) an interacting-hand prior for generative infilling and to refine the interaction dynamics, ensuring plausible recovery under (self-)occlusions, and (iii) hierarchical initialization through a combination of state-of-the-art hand tracking methods. Through extensive evaluations on both in-the-wild and indoor datasets, we show that our approach significantly outperforms state-of-the-art methods in terms of 4D global mesh recovery. This establishes a new benchmark for hand motion reconstruction from monocular video with moving cameras. Our project page is at https://dyn-hamr.github.io/.