Despite the promising performance of current 3D human pose estimation
techniques, understanding and enhancing their generalization on challenging
in-the-wild videos remain an open problem. In this work, we focus on the
robustness of 2D-to-3D pose lifters. To this end, we develop two benchmark
datasets, namely Human3.6M-C and HumanEva-I-C, to examine the robustness of
video-based 3D pose lifters to a wide range of common video corruptions
including temporary occlusion, motion blur, and pixel-level noise. We observe
the poor generalization of state-of-the-art 3D pose lifters in the presence of
corruption and establish two techniques to tackle this issue. First, we
introduce Temporal Additive Gaussian Noise (TAGN) as a simple yet effective 2D
input pose data augmentation. Additionally, to incorporate the confidence
scores output by the 2D pose detectors, we design a confidence-aware
convolution (CA-Conv) block. Extensively tested on corrupted videos, the
proposed strategies consistently boost the robustness of 3D pose lifters and
serve as new baselines for future research.

当前的 3D 人体姿势估计技术虽然表现出色，但在复杂的野外视频中理解和提升它们的普适性仍然是一个开放的问题。本文聚焦于 2D 到 3D 姿势提升器的稳健性，并开发了两个基准数据集来检验视频 - based 3D 姿势提升器对包括临时遮挡、动态模糊和像素级噪声在内的一系列常见视频污染的稳健性。我们观察到现有的最先进的 3D 姿势提升器在存在污染的情况下的普适性较差，并提出了两种应对这一问题的技术。首先，我们引入了时间加性高斯噪声 (TAGN) 作为一种简单而有效的 2D 输入姿势数据增强技术。此外，为了将 2D 姿势检测器输出的置信度得分纳入考虑，我们设计了一种置信度感知的卷积 (CA-Conv) 块。通过在受损视频上广泛测试，所提出的策略不断提升了 3D 姿势提升器的稳健性，并为未来研究建立了新的基准。