Prior research has shown that deep models can estimate the pressure applied by a hand to a surface based on a single RGB image. Training these models requires high-resolution pressure measurements that are difficult to obtain with physical sensors. Additionally, even experts cannot reliably annotate pressure from images. Thus, data collection is a critical barrier to generalization and improved performance. We present a novel approach that enables training data to be efficiently captured from unmodified surfaces with only an RGB camera and a cooperative participant. Our key insight is that people can be prompted to perform actions that correspond with categorical labels (contact labels) describing contact pressure, such as using a specific fingertip to make low-force contact. We present ContactLabelNet, which visually estimates pressure applied by fingertips. With the use of contact labels, ContactLabelNet achieves improved performance, generalizes to novel surfaces, and outperforms models from prior work.

翻译：先前的研究显示,深层模型可以根据单一的 RGB 图像估计手对表面的压力。 培训这些模型需要使用物理传感器很难获得的高分辨率压力测量。 此外, 即使专家也无法可靠地说明图像的压力。 因此, 数据收集是普及和改进性能的关键障碍。 我们提出了一个新颖的方法, 使培训数据能够从未经修改的表面中高效地采集, 只有 RGB 相机和一位合作参与者。 我们的关键洞察力是, 人们可以被催动执行与描述接触压力的直线标签( 接触标签) 相对应的行动, 比如使用特定的指尖进行低强度接触。 我们展示了ContectLabelNet, 用于直观估计指尖应用的压力。 通过使用接触标签, ContectLabelNet 能够提高性能, 向新面进行概括, 并超越先前工作的模型 。