# Pose Magic: Efficient and Temporally Consistent Human Pose Estimation with a Hybrid Mamba-GCN Network

arXiv: https://arxiv.org/abs/2408.02922 · HTML: https://mlsanity.com/paper/2408.02922/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Placed in Video, motion and generative Mamba models, one of 10 directions in State-space sequence models (S4, Mamba).
- Builds on 28 of its 49 references that are in the map.
- First posted on arXiv 6 Aug 2024.

## Placed in

- State-space sequence models (S4, Mamba) / [Video, motion and generative Mamba models](https://mlsanity.com/ssm/video-motion-and-generative-mamba-models/)

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

- [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)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2312.00752/) (2023)
- [Gaussian Error Linear Units (GELUs)](https://mlsanity.com/paper/1606.08415/) (2016)
- [Efficiently Modeling Long Sequences with Structured State Spaces](https://mlsanity.com/paper/2111.00396/) (2021)
- [Stacked Hourglass Networks for Human Pose Estimation](https://mlsanity.com/paper/1603.06937/) (2016)
- [Simplified State Space Layers for Sequence Modeling](https://mlsanity.com/paper/2208.04933/) (2022)
- [Monocular 3D Human Pose Estimation In The Wild Using Improved CNN Supervision](https://mlsanity.com/paper/1611.09813/) (2016)
- [3D human pose estimation in video with temporal convolutions and semi-supervised training](https://mlsanity.com/paper/1811.11742/) (2018)
- [Diagonal State Spaces are as Effective as Structured State Spaces](https://mlsanity.com/paper/2203.14343/) (2022)
- [Cascaded Pyramid Network for Multi-Person Pose Estimation](https://mlsanity.com/paper/1711.07319/) (2017)
- [3D Human Pose Estimation with Spatial and Temporal Transformers](https://mlsanity.com/paper/2103.10455/) (2021)
- [Semantic Graph Convolutional Networks for 3D Human Pose Regression](https://mlsanity.com/paper/1904.03345/) (2019)
- [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)
- [MixSTE: Seq2seq Mixed Spatio-Temporal Encoder for 3D Human Pose Estimation in Video](https://mlsanity.com/paper/2203.00859/) (2022)
- [Not All Tokens Are Equal: Human-centric Visual Analysis via Token Clustering Transformer](https://mlsanity.com/paper/2204.08680/) (2022)
- [Cross View Fusion for 3D Human Pose Estimation](https://mlsanity.com/paper/1909.01203/) (2019)
- [Learning Multi-dimensional Edge Feature-based AU Relation Graph for Facial Action Unit Recognition](https://mlsanity.com/paper/2205.01782/) (2022)
- [Diffusion-Based 3D Human Pose Estimation with Multi-Hypothesis Aggregation](https://mlsanity.com/paper/2303.11579/) (2023)
- [MotionAGFormer: Enhancing 3D Human Pose Estimation with a Transformer-GCNFormer Network](https://mlsanity.com/paper/2310.16288/) (2023)
- [GLA-GCN: Global-local Adaptive Graph Convolutional Network for 3D Human Pose Estimation from Monocular Video](https://mlsanity.com/paper/2307.05853/) (2023)
- [Uplift and Upsample: Efficient 3D Human Pose Estimation with Uplifting Transformers](https://mlsanity.com/paper/2210.06110/) (2022)
- [Trajectory Space Factorization for Deep Video-Based 3D Human Pose Estimation](https://mlsanity.com/paper/1908.08289/) (2019)
- [Vid2Player: Controllable Video Sprites that Behave and Appear like Professional Tennis Players](https://mlsanity.com/paper/2008.04524/) (2020)
- [Lifting by Image -- Leveraging Image Cues for Accurate 3D Human Pose Estimation](https://mlsanity.com/paper/2312.15636/) (2023)

## Built on by (most cited first, 12 of 12)

- [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)
- [Human-in-Context: Unified Cross-Domain 3D Human Motion Modeling via In-Context Learning](https://mlsanity.com/paper/2508.10897/) (2025)
- [Mamba-Driven Topology Fusion for Monocular 3D Human Pose Estimation](https://mlsanity.com/paper/2505.20611/) (2025)
- [FastDDHPose: Towards Unified, Efficient, and Disentangled 3D Human Pose Estimation](https://mlsanity.com/paper/2512.14162/) (2025)
- [SasMamba: A Lightweight Structure-Aware Stride State Space Model for 3D Human Pose Estimation](https://mlsanity.com/paper/2511.08872/) (2025)
- [Superman: Unifying Skeleton and Vision for Human Motion Perception and Generation](https://mlsanity.com/paper/2602.02401/) (2026)
- [KASportsFormer: Kinematic Anatomy Enhanced Transformer for 3D Human Pose Estimation on Short Sports Scene Video](https://mlsanity.com/paper/2507.20763/) (2025)
- [PRGCN: A Graph Memory Network for Cross-Sequence Pattern Reuse in 3D Human Pose Estimation](https://mlsanity.com/paper/2510.19475/) (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)

## Abstract (arXiv)

Current state-of-the-art (SOTA) methods in 3D Human Pose Estimation (HPE) are primarily based on Transformers. However, existing Transformer-based 3D HPE backbones often encounter a trade-off between accuracy and computational efficiency. To resolve the above dilemma, in this work, we leverage recent advances in state space models and utilize Mamba for high-quality and efficient long-range modeling. Nonetheless, Mamba still faces challenges in precisely exploiting local dependencies between joints. To address these issues, we propose a new attention-free hybrid spatiotemporal architecture named Hybrid Mamba-GCN (Pose Magic). This architecture introduces local enhancement with GCN by capturing relationships between neighboring joints, thus producing new representations to complement Mamba's outputs. By adaptively fusing representations from Mamba and GCN, Pose Magic demonstrates superior capability in learning the underlying 3D structure. To meet the requirements of real-time inference, we also provide a fully causal version. Extensive experiments show that Pose Magic achieves new SOTA results (downarrow 0.9 mm) while saving 74.1% FLOPs. In addition, Pose Magic exhibits optimal motion consistency and the ability to generalize to unseen sequence lengths.