论文标题
基于生成模型的救援损失：一种克服基于深度的手姿势估计的注释错误的方法
Generative Model-Based Loss to the Rescue: A Method to Overcome Annotation Errors for Depth-Based Hand Pose Estimation
论文作者
论文摘要
我们建议将基于模型的生成损失用于基于体积手模型的深度图像上的训练手姿势估计器。这种额外的损失允许训练手动姿势估计器，该估计器准确地渗透了整个21个手关键点，而仅对6个易于宣布的关键点（指尖和手腕）使用监督。我们表明，我们的部分监督方法获得了与实施表达一致性的完全监督方法相媲美的结果。此外，我们第一次证明了这种方法可用于在具有错误注释的数据集上训练，即带有明显的测量错误的“地面真相”，同时获得比给定的“地面真相”更好地解释深度图像的预测。
We propose to use a model-based generative loss for training hand pose estimators on depth images based on a volumetric hand model. This additional loss allows training of a hand pose estimator that accurately infers the entire set of 21 hand keypoints while only using supervision for 6 easy-to-annotate keypoints (fingertips and wrist). We show that our partially-supervised method achieves results that are comparable to those of fully-supervised methods which enforce articulation consistency. Moreover, for the first time we demonstrate that such an approach can be used to train on datasets that have erroneous annotations, i.e. "ground truth" with notable measurement errors, while obtaining predictions that explain the depth images better than the given "ground truth".
