PoseMamba：基于双向全局-局部时空状态空间模型的单目3D人体姿态估计
PoseMamba: Monocular 3D Human Pose Estimation with Bidirectional Global-Local Spatio-Temporal State Space Model
AI总结：
针对现有Transformer方法在3D人体姿态估计中复杂度高和时空建模不足的问题，提出基于状态空间模型的PoseMamba，通过双向全局-局部时空建模和重排序策略，在Human3.6M和MPI-INF-3DHP上达到最先进性能，且模型更小、计算成本更低。
摘要：
Transformer 显著推进了 3D 人体姿态估计（HPE）领域的发展。然而，现有的基于 Transformer 的方法主要使用自注意力机制进行时空建模，这导致了二次复杂度、时空关系的单向建模以及时空相关性学习不足的问题。近期，利用状态空间模型（SSM）的 Mamba 架构，在多种视觉任务中展现了优越的长距离建模能力，且具有线性复杂度。在本文中，我们提出了 PoseMamba，一种新颖的、纯 SSM 的、具有线性复杂度的单目视频 3D 人体姿态估计方法。具体来说，我们提出了一个双向全局-局部时空 SSM 块，该块全面建模了单个帧内的人体关节关系以及跨帧的时间相关性。在这个双向全局-局部时空 SSM 块中，我们引入了一种重排序策略以增强 SSM 的局部建模能力。该策略提供了一种更符合逻辑的几何扫描顺序，并将其与全局 SSM 集成，从而形成了一种组合的全局-局部空间扫描。我们使用两个基准数据集：Human3.6M 和 MPI-INF-3DHP，对我们的方法进行了定量和定性评估。大量实验表明，PoseMamba 在两个数据集上都达到了最先进的性能，同时保持了更小的模型尺寸并降低了计算成本。代码和模型将发布。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
