# PoseMamba: Monocular 3D Human Pose Estimation with Bidirectional Global-Local Spatio-Temporal State Space Model

arXiv: https://arxiv.org/abs/2408.03540 · HTML: https://mlsanity.com/paper/2408.03540/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Aug 2024.

## Built on by (most cited first, 15 of 15)

- [High-Resolution Spatiotemporal Modeling with Global-Local State Space Models for Video-Based Human Pose Estimation](https://mlsanity.com/paper/2510.11017/) (2025)
- [A Structure-aware and Motion-adaptive Framework for 3D Human Pose Estimation with Mamba](https://mlsanity.com/paper/2507.19852/) (2025)
- [QuaMo: Quaternion Motions for Vision-based 3D Human Kinematics Capture](https://mlsanity.com/paper/2601.19580/) (2026)
- [Mamba-Driven Topology Fusion for Monocular 3D Human Pose Estimation](https://mlsanity.com/paper/2505.20611/) (2025)
- [ConMamba: Contrastive Vision Mamba for Plant Disease Detection](https://mlsanity.com/paper/2506.03213/) (2025)
- [MamKPD: A Simple Mamba Baseline for Real-Time 2D Keypoint Detection](https://mlsanity.com/paper/2412.01422/) (2024)
- [SasMamba: A Lightweight Structure-Aware Stride State Space Model for 3D Human Pose Estimation](https://mlsanity.com/paper/2511.08872/) (2025)
- [VIMCAN: Visual-Inertial 3D Human Pose Estimation with Hybrid Mamba-Cross-Attention Network](https://mlsanity.com/paper/2605.07552/) (2026)
- [Efficient Diffusion-Based 3D Human Pose Estimation with Hierarchical Temporal Pruning](https://mlsanity.com/paper/2508.21363/) (2025)
- [DF-Mamba: Deformable State Space Modeling for 3D Hand Pose Estimation in Interactions](https://mlsanity.com/paper/2512.02727/) (2025)
- [Towards Geometry-Aware and Motion-Guided Video Human Mesh Recovery](https://mlsanity.com/paper/2601.21376/) (2026)
- [L2A: Learning to Accumulate Pose History for Accurate 3D Human Pose Estimation](https://mlsanity.com/paper/2605.08806/) (2026)
- [HYPERPOSE: Hyperbolic Kinematic Phase-Space Attention for 3D Human Pose Estimation](https://mlsanity.com/paper/2605.10100/) (2026)
- [Pose-to-Biomechanics: Bridging 3D Human Pose Estimation and Biomechanical Attribute Prediction](https://mlsanity.com/paper/2607.08725/) (2026)
- [MuyBridge: Mobile Human Center-of-Mass Estimation from Monocular Video via Sparse Fusion](https://mlsanity.com/paper/2609.02854/) (2026)

## Abstract (arXiv)

Transformers have significantly advanced the field of 3D human pose estimation (HPE). However, existing transformer-based methods primarily use self-attention mechanisms for spatio-temporal modeling, leading to a quadratic complexity, unidirectional modeling of spatio-temporal relationships, and insufficient learning of spatial-temporal correlations. Recently, the Mamba architecture, utilizing the state space model (SSM), has exhibited superior long-range modeling capabilities in a variety of vision tasks with linear complexity. In this paper, we propose PoseMamba, a novel purely SSM-based approach with linear complexity for 3D human pose estimation in monocular video. Specifically, we propose a bidirectional global-local spatio-temporal SSM block that comprehensively models human joint relations within individual frames as well as temporal correlations across frames. Within this bidirectional global-local spatio-temporal SSM block, we introduce a reordering strategy to enhance the local modeling capability of the SSM. This strategy provides a more logical geometric scanning order and integrates it with the global SSM, resulting in a combined global-local spatial scan. We have quantitatively and qualitatively evaluated our approach using two benchmark datasets: Human3.6M and MPI-INF-3DHP. Extensive experiments demonstrate that PoseMamba achieves state-of-the-art performance on both datasets while maintaining a smaller model size and reducing computational costs. The code and models will be released.