arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2303.14747cs.CV
收藏

基于视频的三维人体姿态和形状估计的全局到局部建模

Global-to-Local Modeling for Video-based 3D Human Pose and Shape Estimation

Zhejiang University(浙江大学);DAMO Academy, Alibaba Group(阿里巴巴集团达摩院)

Xiaolong Shen, Zongxin Yang, Xiaohan Wang, Jianxin Ma, Chang Zhou, Yi Yang

摘要:

基于视频的3D人体姿态和形状估计通过帧内精度和帧间平滑度进行评估。虽然这两个度量负责不同范围的时间一致性,但是现有技术的方法将它们视为统一的问题并且使用单调的建模结构(例如,RNN或基于注意力的块)来设计他们的网络。然而,使用单一类型的建模结构很难平衡短期和长期时间相关性的学习,并且可能使网络偏向其中之一,导致不期望的预测,如全局位置偏移,时间不一致和局部细节不足。为了解决这些问题,我们建议在端到端的框架,全球到本地Transformer(GLoT)的长期和短期相关性的建模结构解耦。首先,引入全局Transformer,并采用掩蔽姿态和形状估计策略进行长期建模。该策略通过随机掩蔽多个帧的特征,激励全局Transformer学习更多的帧间相关性。其次,本地Transformer负责利用人体网格上的本地细节,并通过利用交叉注意力与全局Transformer进行交互。此外,层次空间相关回归进一步引入细化帧内估计解耦的全局-局部表示和隐式运动约束。我们的GLoT超越了以前最先进的方法,在流行的基准上具有最低的模型参数,即,3DPW、MPI-INF-3DHP和Human3.6M。代码可在https://github.com/sxl142/GLoT上获得。

英文摘要:

Video-based 3D human pose and shape estimations are evaluated by intra-frame accuracy and inter-frame smoothness. Although these two metrics are responsible for different ranges of temporal consistency, existing state-of-the-art methods treat them as a unified problem and use monotonous modeling structures (e.g., RNN or attention-based block) to design their networks. However, using a single kind of modeling structure is difficult to balance the learning of short-term and long-term temporal correlations, and may bias the network to one of them, leading to undesirable predictions like global location shift, temporal inconsistency, and insufficient local details. To solve these problems, we propose to structurally decouple the modeling of long-term and short-term correlations in an end-to-end framework, Global-to-Local Transformer (GLoT). First, a global transformer is introduced with a Masked Pose and Shape Estimation strategy for long-term modeling. The strategy stimulates the global transformer to learn more inter-frame correlations by randomly masking the features of several frames. Second, a local transformer is responsible for exploiting local details on the human mesh and interacting with the global transformer by leveraging cross-attention. Moreover, a Hierarchical Spatial Correlation Regressor is further introduced to refine intra-frame estimations by decoupled global-local representation and implicit kinematic constraints. Our GLoT surpasses previous state-of-the-art methods with the lowest model parameters on popular benchmarks, i.e., 3DPW, MPI-INF-3DHP, and Human3.6M. Codes are available at https://github.com/sxl142/GLoT.

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。

↑