终身领域自适应3D人体姿态估计
Lifelong Domain Adaptive 3D Human Pose Estimation
AI总结：
本文提出了一种终身领域自适应3D人体姿态估计方法，通过生成对抗网络框架解决领域偏移和灾难性遗忘问题，提升跨域姿态估计性能。
摘要：
3D人体姿态估计（3D HPE）在各种应用中至关重要，从人重识别和动作识别到虚拟现实。然而，依赖于在受控环境中收集的标注3D数据进行训练，对在现实世界中的泛化能力提出了挑战。现有的领域自适应（DA）范式，如通用DA和源无关DA对于3D HPE，忽略了非平稳目标姿态数据集的问题。为了解决这些挑战，我们提出了一种新的任务，称为终身领域自适应3D HPE。据我们所知，我们是首次将终身领域自适应引入3D HPE任务。在这一终身DA设置中，姿态估计器首先在源域上预训练，然后适应于不同的目标域。此外，在适应当前目标域时，姿态估计器无法访问源域和所有先前的目标域。3D HPE的终身DA涉及在适应当前域姿态时克服挑战，并保留来自先前域的知识，特别是对抗灾难性遗忘。我们提出了一种创新的生成对抗网络（GAN）框架，该框架结合了3D姿态生成器、2D姿态判别器和3D姿态估计器。该框架有效缓解了领域偏移并对齐原始和增强的姿态。此外，我们构建了一种新的3D姿态生成器范式，整合了姿态感知、时间感知和领域感知的知识，以增强当前域的适应并缓解对先前域的灾难性遗忘。我们的方法通过在多样化的领域自适应3D HPE数据集上的广泛实验展示了优越的性能。
英文摘要：
3D Human Pose Estimation (3D HPE) is vital in various applications, from person re-identification and action recognition to virtual reality. However, the reliance on annotated 3D data collected in controlled environments poses challenges for generalization to diverse in-the-wild scenarios. Existing domain adaptation (DA) paradigms like general DA and source-free DA for 3D HPE overlook the issues of non-stationary target pose datasets. To address these challenges, we propose a novel task named lifelong domain adaptive 3D HPE. To our knowledge, we are the first to introduce the lifelong domain adaptation to the 3D HPE task. In this lifelong DA setting, the pose estimator is pretrained on the source domain and subsequently adapted to distinct target domains. Moreover, during adaptation to the current target domain, the pose estimator cannot access the source and all the previous target domains. The lifelong DA for 3D HPE involves overcoming challenges in adapting to current domain poses and preserving knowledge from previous domains, particularly combating catastrophic forgetting. We present an innovative Generative Adversarial Network (GAN) framework, which incorporates 3D pose generators, a 2D pose discriminator, and a 3D pose estimator. This framework effectively mitigates domain shifts and aligns original and augmented poses. Moreover, we construct a novel 3D pose generator paradigm, integrating pose-aware, temporal-aware, and domain-aware knowledge to enhance the current domain's adaptation and alleviate catastrophic forgetting on previous domains. Our method demonstrates superior performance through extensive experiments on diverse domain adaptive 3D HPE datasets.
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。
