# Sparkle: A Robust and Versatile Representation for Point Cloud based Human Motion Capture

arXiv: https://arxiv.org/abs/2604.00857 · HTML: https://mlsanity.com/paper/2604.00857/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 36 of its 51 references that are in the map.
- First posted on arXiv 1 Apr 2026.

## Builds on (most cited first, 30 of 36)

- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [End-to-end Recovery of Human Shape and Pose](https://mlsanity.com/paper/1712.06584/) (2017)
- [ByteTrack: Multi-Object Tracking by Associating Every Detection Box](https://mlsanity.com/paper/2110.06864/) (2021)
- [ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation](https://mlsanity.com/paper/2204.12484/) (2022)
- [HybrIK: A Hybrid Analytical-Neural Inverse Kinematics Solution for 3D Human Pose and Shape Estimation](https://mlsanity.com/paper/2011.14672/) (2020)
- [InterGen: Diffusion-based Multi-human Motion Generation under Complex Interactions](https://mlsanity.com/paper/2304.05684/) (2023)
- [WHAM: Reconstructing World-grounded Humans with Accurate 3D Motion](https://mlsanity.com/paper/2312.07531/) (2023)
- [SoftGroup for 3D Instance Segmentation on Point Clouds](https://mlsanity.com/paper/2203.01509/) (2022)
- [RTMPose: Real-Time Multi-Person Pose Estimation based on MMPose](https://mlsanity.com/paper/2303.07399/) (2023)
- [PoseTrack: A Benchmark for Human Pose Estimation and Tracking](https://mlsanity.com/paper/1710.10000/) (2017)
- [Physical Inertial Poser (PIP): Physics-aware Real-time Human Motion Tracking from Sparse Inertial Sensors](https://mlsanity.com/paper/2203.08528/) (2022)
- [World-Grounded Human Motion Recovery via Gravity-View Coordinates](https://mlsanity.com/paper/2409.06662/) (2024)
- [HuMMan: Multi-Modal 4D Human Dataset for Versatile Sensing and Modeling](https://mlsanity.com/paper/2204.13686/) (2022)
- [TRAM: Global Trajectory and Motion of 3D Humans from in-the-wild Videos](https://mlsanity.com/paper/2403.17346/) (2024)
- [TRACE: 5D Temporal Regression of Avatars with Dynamic Cameras in 3D Environments](https://mlsanity.com/paper/2306.02850/) (2023)
- [Hi4D: 4D Instance Segmentation of Close Human Interaction](https://mlsanity.com/paper/2303.15380/) (2023)
- [EventCap: Monocular 3D Capture of High-Speed Human Motions using an Event Camera](https://mlsanity.com/paper/1908.11505/) (2019)
- [Playing for 3D Human Recovery](https://mlsanity.com/paper/2110.07588/) (2021)
- [SLOPER4D: A Scene-Aware Dataset for Global 4D Human Pose Estimation in Urban Environments](https://mlsanity.com/paper/2303.09095/) (2023)
- [LiDAR-aid Inertial Poser: Large-scale Human Motion Capture by Sparse Inertial and LiDAR Sensors](https://mlsanity.com/paper/2205.15410/) (2022)
- [3D Human Mesh Estimation from Virtual Markers](https://mlsanity.com/paper/2303.11726/) (2023)
- [HSC4D: Human-centered 4D Scene Capture in Large-scale Indoor-outdoor Space Using Wearable IMUs and LiDAR](https://mlsanity.com/paper/2203.09215/) (2022)
- [3D Human Pose Estimation in RGBD Images for Robotic Task Learning](https://mlsanity.com/paper/1803.02622/) (2018)
- [LiDARCap: Long-range Marker-less 3D Human Motion Capture with LiDAR Point Clouds](https://mlsanity.com/paper/2203.14698/) (2022)
- [Recurrent Human Pose Estimation](https://mlsanity.com/paper/1605.02914/) (2016)
- [PedX: Benchmark Dataset for Metric 3D Pose Estimation of Pedestrians in Complex Urban Intersections](https://mlsanity.com/paper/1809.03605/) (2018)
- [LiveHPS: LiDAR-based Scene-level Human Pose and Shape Estimation in Free Environment](https://mlsanity.com/paper/2402.17171/) (2024)
- [VoteHMR: Occlusion-Aware Voting Network for Robust 3D Human Mesh Recovery from Partial Point Clouds](https://mlsanity.com/paper/2110.08729/) (2021)
- [Personalizing Human Video Pose Estimation](https://mlsanity.com/paper/1511.06676/) (2015)
- [WorldPose: A World Cup Dataset for Global 3D Human Pose Estimation](https://mlsanity.com/paper/2501.02771/) (2025)

## Abstract (arXiv)

Point cloud-based motion capture leverages rich spatial geometry and privacy-preserving sensing, but learning robust representations from noisy, unstructured point clouds remains challenging. Existing approaches face a struggle trade-off between point-based methods (geometrically detailed but noisy) and skeleton-based ones (robust but oversimplified). We address the fundamental challenge: how to construct an effective representation for human motion capture that can balance expressiveness and robustness. In this paper, we propose Sparkle, a structured representation unifying skeletal joints and surface anchors with explicit kinematic-geometric factorization. Our framework, SparkleMotion, learns this representation through hierarchical modules embedding geometric continuity and kinematic constraints. By explicitly disentangling internal kinematic structure from external surface geometry, SparkleMotion achieves state-of-the-art performance not only in accuracy but crucially in robustness and generalization under severe domain shifts, noise, and occlusion. Extensive experiments demonstrate our superiority across diverse sensor types and challenging real-world scenarios.