# Every Angle Is Worth A Second Glance: Mining Kinematic Skeletal Structures from Multi-view Joint Cloud

arXiv: https://arxiv.org/abs/2502.02936 · HTML: https://mlsanity.com/paper/2502.02936/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 53 references that are in the map.
- First posted on arXiv 5 Feb 2025.

## Builds on (most cited first, 26 of 26)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains](https://mlsanity.com/paper/2006.10739/) (2020)
- [OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields](https://mlsanity.com/paper/1812.08008/) (2018)
- [Learning to Reconstruct 3D Human Pose and Shape via Model-fitting in the Loop](https://mlsanity.com/paper/1909.12828/) (2019)
- [3D human pose estimation in video with temporal convolutions and semi-supervised training](https://mlsanity.com/paper/1811.11742/) (2018)
- [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)
- [AlphaPose: Whole-Body Regional Multi-Person Pose Estimation and Tracking in Real-Time](https://mlsanity.com/paper/2211.03375/) (2022)
- [4D Association Graph for Realtime Multi-person Motion Capture Using Multiple Video Cameras](https://mlsanity.com/paper/2002.12625/) (2020)
- [Faster VoxelPose: Real-time 3D Human Pose Estimation by Orthographic Projection](https://mlsanity.com/paper/2207.10955/) (2022)
- [Multi-View Multi-Person 3D Pose Estimation with Plane Sweep Stereo](https://mlsanity.com/paper/2104.02273/) (2021)
- [Graph-Based 3D Multi-Person Pose Estimation Using Multi-View Images](https://mlsanity.com/paper/2109.05885/) (2021)
- [ElePose: Unsupervised 3D Human Pose Estimation by Predicting Camera Elevation and Learning Normalizing Flows on 2D Poses](https://mlsanity.com/paper/2112.07088/) (2021)
- [Neural MoCon: Neural Motion Control for Physically Plausible Human Motion Capture](https://mlsanity.com/paper/2203.14065/) (2022)
- [PoseTriplet: Co-evolving 3D Human Pose Estimation, Imitation, and Hallucination under Self-supervision](https://mlsanity.com/paper/2203.15625/) (2022)
- [TEMPO: Efficient Multi-View Pose Estimation, Tracking, and Forecasting](https://mlsanity.com/paper/2309.07910/) (2023)
- [SelfPose3d: Self-Supervised Multi-Person Multi-View 3d Pose Estimation](https://mlsanity.com/paper/2404.02041/) (2024)
- [Adaptive Multi-view and Temporal Fusing Transformer for 3D Human Pose Estimation](https://mlsanity.com/paper/2110.05092/) (2021)
- [MotionAug: Augmentation with Physical Correction for Human Motion Prediction](https://mlsanity.com/paper/2203.09116/) (2022)
- [Towards Robust and Smooth 3D Multi-Person Pose Estimation from Monocular Videos in the Wild](https://mlsanity.com/paper/2309.08644/) (2023)
- [A Dual-Masked Auto-Encoder for Robust Motion Capture with Spatial-Temporal Skeletal Token Completion](https://mlsanity.com/paper/2207.07381/) (2022)
- [Exploring Latent Cross-Channel Embedding for Accurate 3D Human Pose Reconstruction in a Diffusion Framework](https://mlsanity.com/paper/2401.09836/) (2024)

## Built on by (most cited first, 2 of 2)

- [Deep Compositional Phase Diffusion for Long Motion Sequence Generation](https://mlsanity.com/paper/2510.14427/) (2025)
- [Learning Context-Adaptive Motion Priors for Masked Motion Diffusion Models with Efficient Kinematic Attention Aggregation](https://mlsanity.com/paper/2603.07697/) (2026)

## Abstract (arXiv)

Multi-person motion capture over sparse angular observations is a challenging problem under interference from both self- and mutual-occlusions. Existing works produce accurate 2D joint detection, however, when these are triangulated and lifted into 3D, available solutions all struggle in selecting the most accurate candidates and associating them to the correct joint type and target identity. As such, in order to fully utilize all accurate 2D joint location information, we propose to independently triangulate between all same-typed 2D joints from all camera views regardless of their target ID, forming the Joint Cloud. Joint Cloud consist of both valid joints lifted from the same joint type and target ID, as well as falsely constructed ones that are from different 2D sources. These redundant and inaccurate candidates are processed over the proposed Joint Cloud Selection and Aggregation Transformer (JCSAT) involving three cascaded encoders which deeply explore the trajectile, skeletal structural, and view-dependent correlations among all 3D point candidates in the cross-embedding space. An Optimal Token Attention Path (OTAP) module is proposed which subsequently selects and aggregates informative features from these redundant observations for the final prediction of human motion. To demonstrate the effectiveness of JCSAT, we build and publish a new multi-person motion capture dataset BUMocap-X with complex interactions and severe occlusions. Comprehensive experiments over the newly presented as well as benchmark datasets validate the effectiveness of the proposed framework, which outperforms all existing state-of-the-art methods, especially under challenging occlusion scenarios.