# COMPOSE: Hypergraph Cover Optimization for Multi-view 3D Human Pose Estimation

arXiv: https://arxiv.org/abs/2601.09698 · HTML: https://mlsanity.com/paper/2601.09698/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 36 of its 70 references that are in the map.
- First posted on arXiv 14 Jan 2026.

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

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Deep High-Resolution Representation Learning for Human Pose Estimation](https://mlsanity.com/paper/1902.09212/) (2019)
- [ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation](https://mlsanity.com/paper/2204.12484/) (2022)
- [A simple yet effective baseline for 3d human pose estimation](https://mlsanity.com/paper/1705.03098/) (2017)
- [BoT-SORT: Robust Associations Multi-Pedestrian Tracking](https://mlsanity.com/paper/2206.14651/) (2022)
- [Deep Learning-Based Human Pose Estimation: A Survey](https://mlsanity.com/paper/2012.13392/) (2020)
- [MotionBERT: A Unified Perspective on Learning Human Motion Representations](https://mlsanity.com/paper/2210.06551/) (2022)
- [Learnable Triangulation of Human Pose](https://mlsanity.com/paper/1905.05754/) (2019)
- [SyncDiffusion: Coherent Montage via Synchronized Joint Diffusions](https://mlsanity.com/paper/2306.05178/) (2023)
- [RT-DETRv2: Improved Baseline with Bag-of-Freebies for Real-Time Detection Transformer](https://mlsanity.com/paper/2407.17140/) (2024)
- [Fast and Robust Multi-Person 3D Pose Estimation from Multiple Views](https://mlsanity.com/paper/1901.04111/) (2019)
- [Learning Generalisable Omni-Scale Representations for Person Re-Identification](https://mlsanity.com/paper/1910.06827/) (2019)
- [ViTPose++: Vision Transformer for Generic Body Pose Estimation](https://mlsanity.com/paper/2212.04246/) (2022)
- [Direct Multi-view Multi-person 3D Pose Estimation](https://mlsanity.com/paper/2111.04076/) (2021)
- [4D Association Graph for Realtime Multi-person Motion Capture Using Multiple Video Cameras](https://mlsanity.com/paper/2002.12625/) (2020)
- [MultiBodySync: Multi-Body Segmentation and Motion Estimation via 3D Scan Synchronization](https://mlsanity.com/paper/2101.06605/) (2021)
- [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)
- [Quantum Permutation Synchronization](https://mlsanity.com/paper/2101.07755/) (2021)
- [Probabilistic Permutation Synchronization using the Riemannian Structure of the Birkhoff Polytope](https://mlsanity.com/paper/1904.05814/) (2019)
- [Dynamic Multi-Person Mesh Recovery From Uncalibrated Multi-View Cameras](https://mlsanity.com/paper/2110.10355/) (2021)
- [SyncTweedies: A General Generative Framework Based on Synchronized Diffusions](https://mlsanity.com/paper/2403.14370/) (2024)
- [Generalizable Human Pose Triangulation](https://mlsanity.com/paper/2110.00280/) (2021)
- [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)
- [Multiple View Geometry Transformers for 3D Human Pose Estimation](https://mlsanity.com/paper/2311.10983/) (2023)
- [Markerless Multi-view 3D Human Pose Estimation: a survey](https://mlsanity.com/paper/2407.03817/) (2024)

## Built on by (most cited first, 1 of 1)

- [TopoOR: A Unified Topological Scene Representation for the Operating Room](https://mlsanity.com/paper/2603.09466/) (2026)

## Abstract (arXiv)

3D human pose estimation from sparse multi-view camera rigs is an essential task for numerous applications, including action recognition, sports analysis, and human-robot interaction. While learned methods dominate the field on benchmarks, they require large annotated datasets; training-free optimization-based methods remain promising as they circumvent 3D supervision by solving a correspondence problem across views from 2D detections. Existing combinatorial formulations rely on pairwise associations to model this correspondence problem and enforce global consistency across views only as a downstream constraint. However, reconciling locally plausible pairwise matches becomes brittle under occlusion and noisy detections, where local errors propagate globally. We propose COMPOSE, which recasts multi-view 3D human pose estimation as a weighted exact-cover optimization over a hypergraph of person hypotheses. Our formulation replaces pairwise association and post-hoc consistency enforcement with a single global combinatorial objective. To address the exponentially large candidate space, we introduce a geometric pruning strategy alongside two complementary solvers: an exact Integer Linear Programming formulation and a scalable relaxation via Belief Propagation. Without any 3D supervision, COMPOSE improves average precision by up to 31 points over the best optimization-based method and 13 points over self-supervised learned methods, demonstrating the effectiveness of higher-order combinatorial association for training-free multi-view 3D human pose estimation.