论文标题
一种简单的方法来提高人类姿势估计精度，通过纠正人类36m数据集的关节回归剂
A Simple Method to Boost Human Pose Estimation Accuracy by Correcting the Joint Regressor for the Human3.6m Dataset
论文作者
论文摘要
许多人类姿势估计方法估计皮肤多人线性（SMPL）模型，并从这些SMPL估计中回归人类关节。在这项工作中，我们表明使用最广泛使用的SMPL到接头线性层（关节回归器）是不准确的，这可能会误导姿势评估结果。为了实现更准确的关节回归器，我们提出了一种创建伪地面真相SMPL姿势的方法，然后可以使用该姿势来训练改进的回归器。具体而言，我们优化了来自最先进方法的SMPL估计值，以使其投影与现场的人类和地面2D关节位置相匹配。尽管由于缺乏实际的地面SMPL，因此该伪地真相的质量在评估方面具有挑战性，但由于人类为360万数据集，但我们定性地表明，我们的联合位置更准确，并且我们的回归器会导致改进的姿势估算结果，而无需进行任何重新研究。我们在https://github.com/ubc-vision/joint-regressor-refinement上发布代码和联合回归器
Many human pose estimation methods estimate Skinned Multi-Person Linear (SMPL) models and regress the human joints from these SMPL estimates. In this work, we show that the most widely used SMPL-to-joint linear layer (joint regressor) is inaccurate, which may mislead pose evaluation results. To achieve a more accurate joint regressor, we propose a method to create pseudo-ground-truth SMPL poses, which can then be used to train an improved regressor. Specifically, we optimize SMPL estimates coming from a state-of-the-art method so that its projection matches the silhouettes of humans in the scene, as well as the ground-truth 2D joint locations. While the quality of this pseudo-ground-truth is challenging to assess due to the lack of actual ground-truth SMPL, with the Human 3.6m dataset, we qualitatively show that our joint locations are more accurate and that our regressor leads to improved pose estimations results on the test set without any need for retraining. We release our code and joint regressor at https://github.com/ubc-vision/joint-regressor-refinement
