Conventional 3D human pose estimation relies on first detecting 2D body keypoints and then solving the 2D to 3D correspondence problem.Despite the promising results, this learning paradigm is highly dependent on the quality of the 2D keypoint detector, which is inevitably fragile to occlusions and out-of-image absences.In this paper,we propose a novel Pose Orientation Net (PONet) that is able to robustly estimate 3D pose by learning orientations only, hence bypassing the error-prone keypoint detector in the absence of image evidence. For images with partially invisible limbs, PONet estimates the 3D orientation of these limbs by taking advantage of the local image evidence to recover the 3D pose.Moreover, PONet is competent to infer full 3D poses even from images with completely invisible limbs, by exploiting the orientation correlation between visible limbs to complement the estimated poses,further improving the robustness of 3D pose estimation.We evaluate our method on multiple datasets, including Human3.6M, MPII, MPI-INF-3DHP, and 3DPW. Our method achieves results on par with state-of-the-art techniques in ideal settings, yet significantly eliminates the dependency on keypoint detectors and the corresponding computation burden. In highly challenging scenarios, such as truncation and erasing, our method performs very robustly and yields much superior results as compared to state of the art,demonstrating its potential for real-world applications.

翻译：常规的 3D 人类的外观估计取决于首先检测到 2D 身体键点, 然后解决 2D 至 3D 对应问题。 尽管取得了有希望的结果, 这一学习模式高度依赖于 2D 关键点检测器的质量, 这不可避免地对隔离和图像外缺十分脆弱。 在本文中, 我们提出一个新的 Pose 方向网(PONet), 它只能通过学习方向来强有力地估计 3D 构成, 从而在没有图像证据的情况下绕过易出错的关键点检测器。 对于部分隐形肢体的图像, PONet 利用当地图像证据来恢复 3D 形状, 来估计这些肢体的3D 方向。 Moreover, PONet 有能力将完全从完全隐形的外观图像中推入 3D 。 通过利用可见的四肢之间的定向关系来补充估计的外观, 进一步增强 3D 构成 的稳定性。 我们评估了我们多重数据集的方法, 包括 Human3.6M、 MPII、 MPI- INF-3DHP 3DPP 和 3DPW 3W 的3D 应用方法, 通过利用当地图像 来估计3D 的3D 的3D 来估计, 来估计3D 评估这些三维的3D 的3D 的3D 的3D 的3D 的3D, 通过利用当地图像的精确度 方法,,,, 通过利用当地图像的精确的精确度, 方法, 方法,,,,,,,, 和 和 方法在高度的精确的计算方法,,,, 实现 和高度的精确的精确的,,,,,,,, 方法,,,,,,,,,,,,,,,,,, 在,, 度,,,,,,,,,,,,, 和高度的, 和, 和 高度的,, 高度的,,,,,