Modern multi-layer perceptron (MLP) models have shown competitive results in learning visual representations without self-attention. However, existing MLP models are not good at capturing local details and lack prior knowledge of human body configurations, which limits their modeling power for skeletal representation learning. To address these issues, we propose a simple yet effective graph-reinforced MLP-Like architecture, named GraphMLP, that combines MLPs and graph convolutional networks (GCNs) in a global-local-graphical unified architecture for 3D human pose estimation. GraphMLP incorporates the graph structure of human bodies into an MLP model to meet the domain-specific demand of the 3D human pose, while allowing for both local and global spatial interactions. Furthermore, we propose to flexibly and efficiently extend the GraphMLP to the video domain and show that complex temporal dynamics can be effectively modeled in a simple way with negligible computational cost gains in the sequence length. To the best of our knowledge, this is the first MLP-Like architecture for 3D human pose estimation in a single frame and a video sequence. Extensive experiments show that the proposed GraphMLP achieves state-of-the-art performance on two datasets, i.e., Human3.6M and MPI-INF-3DHP. Code and models are available at https://github.com/Vegetebird/GraphMLP.

翻译：现代多层感知机（MLP）模型在学习视觉表示方面无需自注意力机制即可展现出竞争性结果。然而，现有MLP模型不擅长捕捉局部细节且缺乏人体构型的先验知识，这限制了它们在骨骼表示学习中的建模能力。为解决这些问题，我们提出了一种简单而高效的图增强类MLP架构，命名为GraphMLP，该架构在全局-局部-图形化统一架构中融合了MLP与图卷积网络（GCNs），用于三维人体姿态估计。GraphMLP将人体图结构引入MLP模型以满足三维人体姿态的领域特定需求，同时支持局部与全局空间交互。此外，我们提出灵活且高效地将GraphMLP扩展到视频领域，并展示了在序列长度上以极小的计算成本增量即可通过简单方式有效建模复杂时间动态。据我们所知，这是首个面向单帧与视频序列三维人体姿态估计的类MLP架构。大量实验表明，所提出的GraphMLP在Human3.6M和MPI-INF-3DHP两个数据集上均达到了最先进性能。代码与模型已开源在https://github.com/Vegetebird/GraphMLP。