# Contrastive Multi-Modal Hypergraph Reasoning for 3D Crowd Mesh Recovery

arXiv: https://arxiv.org/abs/2605.13854 · HTML: https://mlsanity.com/paper/2605.13854/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 28 of its 36 references that are in the map.
- First posted on arXiv 1 Apr 2026.

## Builds on (most cited first, 28 of 28)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data](https://mlsanity.com/paper/2401.10891/) (2024)
- [OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields](https://mlsanity.com/paper/1812.08008/) (2018)
- [Hypergraph Neural Networks](https://mlsanity.com/paper/1809.09401/) (2018)
- [CLIFF: Carrying Location Information in Full Frames into Human Pose and Shape Estimation](https://mlsanity.com/paper/2208.00571/) (2022)
- [Monocular, One-stage, Regression of Multiple 3D People](https://mlsanity.com/paper/2008.12272/) (2020)
- [CrowdPose: Efficient Crowded Scenes Pose Estimation and A New Benchmark](https://mlsanity.com/paper/1812.00324/) (2018)
- [FUTR3D: A Unified Sensor Fusion Framework for 3D Detection](https://mlsanity.com/paper/2203.10642/) (2022)
- [Putting People in their Place: Monocular Regression of 3D People in Depth](https://mlsanity.com/paper/2112.08274/) (2021)
- [Coherent Reconstruction of Multiple Humans from a Single Image](https://mlsanity.com/paper/2006.08586/) (2020)
- [Camera Distance-aware Top-down Approach for 3D Multi-person Pose Estimation from a Single RGB Image](https://mlsanity.com/paper/1907.11346/) (2019)
- [GroupNet: Multiscale Hypergraph Neural Networks for Trajectory Prediction with Relational Reasoning](https://mlsanity.com/paper/2204.08770/) (2022)
- [Multi-HMR: Multi-Person Whole-Body Human Mesh Recovery in a Single Shot](https://mlsanity.com/paper/2402.14654/) (2024)
- [Learning to Estimate Robust 3D Human Mesh from In-the-Wild Crowded Scenes](https://mlsanity.com/paper/2104.07300/) (2021)
- [Pixels to Graphs by Associative Embedding](https://mlsanity.com/paper/1706.07365/) (2017)
- [SMAP: Single-Shot Multi-Person Absolute 3D Pose Estimation](https://mlsanity.com/paper/2008.11469/) (2020)
- [Body Meshes as Points](https://mlsanity.com/paper/2105.02467/) (2021)
- [Score-Guided Diffusion for 3D Human Recovery](https://mlsanity.com/paper/2403.09623/) (2024)
- [ImmFusion: Robust mmWave-RGB Fusion for 3D Human Body Reconstruction in All Weather Conditions](https://mlsanity.com/paper/2210.01346/) (2022)
- [Multi-Agent Dynamic Relational Reasoning for Social Robot Navigation](https://mlsanity.com/paper/2401.12275/) (2024)
- [Scene-Aware 3D Multi-Human Motion Capture from a Single Camera](https://mlsanity.com/paper/2301.05175/) (2023)
- [Closely Interactive Human Reconstruction with Proxemics and Physics-Guided Adaption](https://mlsanity.com/paper/2404.11291/) (2024)
- [Reconstructing Groups of People with Hypergraph Relational Reasoning](https://mlsanity.com/paper/2308.15844/) (2023)
- [SAT-HMR: Real-Time Multi-Person 3D Mesh Estimation via Scale-Adaptive Tokens](https://mlsanity.com/paper/2411.19824/) (2024)
- [Crowd3D: Towards Hundreds of People Reconstruction from a Single Image](https://mlsanity.com/paper/2301.09376/) (2023)
- [Reconstructing Close Human Interaction with Appearance and Proxemics Reasoning](https://mlsanity.com/paper/2507.02565/) (2025)
- [DyCrowd: Towards Dynamic Crowd Reconstruction from a Large-scene Video](https://mlsanity.com/paper/2508.12644/) (2025)
- [CrowdRec: 3D Crowd Reconstruction from Single Color Images](https://mlsanity.com/paper/2310.06332/) (2023)

## Abstract (arXiv)

Multi-person 3D reconstruction is pivotal for real-world interaction analysis, yet remains challenging due to severe occlusions and depth ambiguity. Current approaches typically rely on single-modality inputs, which inherently lack geometric guidance. Furthermore, these methods often reconstruct subjects in isolation, neglecting the collective group context essential for resolving ambiguities in crowded scenes. To address these limitations, we propose Contrastive Multi-modal Hypergraph Reasoning to synergize semantic, geometric, and pose cues for crowd reconstruction. We first initialize robust node representations by combining RGB features, geometric priors, and occlusion-aware incomplete poses. Additionally, we introduce a pelvis depth indicator as a global spatial anchor, aligning visual features with a metric-scale-agnostic depth ordering. Subsequently, we construct a shared-topology hypergraph that moves beyond pairwise constraints to model higher-order crowd dynamics. To improve feature fusion, we design a hypergraph-based contrastive learning scheme that jointly enhances intra-modal discriminability and enforces cross-modal orthogonality. This mechanism enables the network to propagate global context effectively, allowing it to infer missing information even under severe occlusion. Extensive experiments on the Panoptic and GigaCrowd benchmarks confirm that our method achieves new state-of-the-art performance. Code and pre-trained models are available at https://github.com/SunMH-try/CoMHR.