Modulated Graph Convolutional Network for 3D Human Pose Estimation
Modulated Graph Convolutional Network for 3D Human Pose Estimation
复制标题
DOI：
10.1109/iccv48922.2021.01128
复制
发表时间：
2021-10
期刊：
影响因子：
--
通讯作者：
Zhiming Zou;Wei Tang
中科院分区：
文献类型：
--
作者：
Zhiming Zou;Wei Tang
最近，图卷积网络(GCN)通过对人体各部分之间的关系进行建模，在三维人体姿势估计(HPE)中取得了良好的性能。然而，大多数以前的GCN方法都有两个主要缺陷。首先，它们共享图形卷积层内每个节点的特征变换。这阻止了他们学习不同身体关节之间的不同关系。其次，该图通常是根据人类骨骼定义的，并不是最优的，因为人类活动经常表现出身体关节自然连接之外的运动模式。为了解决这些局限性，我们引入了一种用于3D HPE的新型调制GCN。它由两个主要组成部分组成：权重调节和亲和力调节。权值调制为不同的节点学习不同的调制向量，从而在保持较小模型尺寸的同时，使不同节点的特征变换解缠。亲和力调制调整GCN中的图结构，以便它可以对人类骨架之外的额外边进行建模。我们研究了几种亲和力调节方法以及正则化的影响。严格的烧蚀研究表明，这两种类型的调制都提高了性能，开销可以忽略不计。与最先进的3D HPE GCNS相比，我们的方法要么显著减少估计误差，例如约10%，同时保持较小的模型大小，要么大幅减少模型大小，例如从4.22m减少到0.29m(减少14.5倍)，同时获得类似的性能。在两个基准测试上的结果表明，我们调制的GCN的性能优于一些最新的技术状态。我们的代码可以在https://github.com/ZhimingZo/Modulated-GCN.上找到
The graph convolutional network (GCN) has recently achieved promising performance of 3D human pose estimation (HPE) by modeling the relationship among body parts. However, most prior GCN approaches suffer from two main drawbacks. First, they share a feature transformation for each node within a graph convolution layer. This prevents them from learning different relations between different body joints. Second, the graph is usually defined according to the human skeleton and is suboptimal because human activities often exhibit motion patterns beyond the natural connections of body joints. To address these limitations, we introduce a novel Modulated GCN for 3D HPE. It consists of two main components: weight modulation and affinity modulation. Weight modulation learns different modulation vectors for different nodes so that the feature transformations of different nodes are disentangled while retaining a small model size. Affinity modulation adjusts the graph structure in a GCN so that it can model additional edges beyond the human skeleton. We investigate several affinity modulation methods as well as the impact of regularizations. Rigorous ablation study indicates both types of modulation improve performance with negligible overhead. Compared with state-of-the-art GCNs for 3D HPE, our approach either significantly reduces the estimation errors, e.g., by around 10%, while retaining a small model size or drastically reduces the model size, e.g., from 4.22M to 0.29M (a 14.5× reduction), while achieving comparable performance. Results on two benchmarks show our Modulated GCN outperforms some recent states of the art. Our code is available at https://github.com/ZhimingZo/Modulated-GCN.