# DisPOSE: Projected Polystochastic Diffusion for Self-Supervised Multi-View 3D Human Pose Estimation

arXiv: https://arxiv.org/abs/2606.07419 · HTML: https://mlsanity.com/paper/2606.07419/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 55 of its 93 references that are in the map.
- First posted on arXiv 5 Jun 2026.

## Builds on (most cited first, 30 of 55)

- [FiLM: Visual Reasoning with a General Conditioning Layer](https://mlsanity.com/paper/1709.07871/) (2017)
- [Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distances](https://mlsanity.com/paper/1306.0895/) (2013)
- [SuperGlue: Learning Feature Matching with Graph Neural Networks](https://mlsanity.com/paper/1911.11763/) (2019)
- [Diffusion Models in Vision: A Survey](https://mlsanity.com/paper/2209.04747/) (2022)
- [Computational Optimal Transport](https://mlsanity.com/paper/1803.00567/) (2018)
- [ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation](https://mlsanity.com/paper/2204.12484/) (2022)
- [Vision Transformer with Deformable Attention](https://mlsanity.com/paper/2201.00520/) (2022)
- [Hypergraph Convolution and Hypergraph Attention](https://mlsanity.com/paper/1901.08150/) (2019)
- [Deep Learning-Based Human Pose Estimation: A Survey](https://mlsanity.com/paper/2012.13392/) (2020)
- [Learning Latent Permutations with Gumbel-Sinkhorn Networks](https://mlsanity.com/paper/1802.08665/) (2018)
- [Learnable Triangulation of Human Pose](https://mlsanity.com/paper/1905.05754/) (2019)
- [You are AllSet: A Multiset Function Framework for Hypergraph Neural Networks](https://mlsanity.com/paper/2106.13264/) (2021)
- [SyncDiffusion: Coherent Montage via Synchronized Joint Diffusions](https://mlsanity.com/paper/2306.05178/) (2023)
- [V2V-PoseNet: Voxel-to-Voxel Prediction Network for Accurate 3D Hand and Human Pose Estimation from a Single Depth Map](https://mlsanity.com/paper/1711.07399/) (2017)
- [Constrained Synthesis with Projected Diffusion Models](https://mlsanity.com/paper/2402.03559/) (2024)
- [mHC: Manifold-Constrained Hyper-Connections](https://mlsanity.com/paper/2512.24880/) (2025)
- [Reflected Diffusion Models](https://mlsanity.com/paper/2304.04740/) (2023)
- [Fast and Robust Multi-Person 3D Pose Estimation from Multiple Views](https://mlsanity.com/paper/1901.04111/) (2019)
- [Stabilized Sparse Scaling Algorithms for Entropy Regularized Transport Problems](https://mlsanity.com/paper/1610.06519/) (2016)
- [SAM 3D Body: Robust Full-Body Human Mesh Recovery](https://mlsanity.com/paper/2602.15989/) (2026)
- [Direct Multi-view Multi-person 3D Pose Estimation](https://mlsanity.com/paper/2111.04076/) (2021)
- [Diffusion Models for Constrained Domains](https://mlsanity.com/paper/2304.05364/) (2023)
- [Learning Skeletal Graph Neural Networks for Hard 3D Pose Estimation](https://mlsanity.com/paper/2108.07181/) (2021)
- [GLA-GCN: Global-local Adaptive Graph Convolutional Network for 3D Human Pose Estimation from Monocular Video](https://mlsanity.com/paper/2307.05853/) (2023)
- [MultiBodySync: Multi-Body Segmentation and Motion Estimation via 3D Scan Synchronization](https://mlsanity.com/paper/2101.06605/) (2021)
- [Mirror Diffusion Models for Constrained and Watermarked Generation](https://mlsanity.com/paper/2310.01236/) (2023)
- [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)
- [Learning Dynamics via Graph Neural Networks for Human Pose Estimation and Tracking](https://mlsanity.com/paper/2106.03772/) (2021)

## Abstract (arXiv)

Recovering 3D human poses for multiple individuals from different camera views is a fundamental bottleneck for analyzing interacting behaviors. Existing self-supervised approaches leverage synthetic catalogues of 3D poses; however, this leads to poor generalization in real-world scenarios due to distribution shifts. We therefore introduce DisPOSE, a self-supervised framework that approximates the inherently discrete multi-view person-assignment problem as a generative diffusion process over the space of polystochastic tensors. By employing differentiable Sinkhorn projections during denoising, our model learns to guide solutions toward valid and feasible assignments based on 2D image priors. The complete 3D skeletons of localized individuals are then regressed using a Hypergraph-Convolutional Decoder that explicitly models relational structures and articulated joints across multiple views. The proposed approach outperforms current state-of-the-art self-supervised methods on standard datasets and demonstrates strong performance on a newly proposed benchmark featuring highly occluded scenes from surgical operating rooms. Our diffusion-based localization demonstrates high label efficiency, retaining 99% of its performance with only 10% of the pseudo-labels. Notably, disentangling the assignment and root regression components while maintaining differentiability makes DisPOSE nearly agnostic to different camera arrangements. Project site and code: https://wngtn.github.io/DisPOSE/