Hand modeling is critical for immersive VR/AR, action understanding, or human healthcare. Existing parametric models account only for hand shape, pose, or texture, without modeling the anatomical attributes like bone, which is essential for realistic hand biomechanics analysis. In this paper, we present PIANO, the first parametric bone model of human hands from MRI data. Our PIANO model is biologically correct, simple to animate, and differentiable, achieving more anatomically precise modeling of the inner hand kinematic structure in a data-driven manner than the traditional hand models based on the outer surface only. Furthermore, our PIANO model can be applied in neural network layers to enable training with a fine-grained semantic loss, which opens up the new task of data-driven fine-grained hand bone anatomic and semantic understanding from MRI or even RGB images. We make our model publicly available.
翻译:手动模型对于浸泡 VR/AR 、 行动理解或人体保健至关重要。 现有的参数模型只考虑手形、 姿势或纹理, 而不进行骨类等解剖属性的模型, 这对于现实的手动生物机理分析至关重要 。 在本文中, 我们介绍PIANO, 人类手部的第一个参数骨类模型, 从 MRI 数据。 我们的PIANO 模型在生物学上是正确的, 简单到动脉, 并且可以区分, 以数据驱动的方式, 实现内手运动结构的解剖精确模型, 而不是以外表为主的传统手型模型。 此外, 我们的PIANO 模型可以应用于神经网络层, 以便能够在精细的语义损失下进行培训。 这开启了数据驱动的精细手骨类解解剖和语义学新任务, 从 MRI 甚至 RGB 图像中开启了新的任务 。 我们公开了我们的模型 。