PIANO - A Parametric Hand Bone Model from Magnetic Resonance Imaging

• Yuwei Li, Minye Wu, Yuyao Zhang, Lan Xu and Jingyi Yu

• https://arxiv.org/pdf/2106.10893v1.pdf  |  Shanghai Engineering Research Center of Intelligent Vision and Imaging, School of Information Science and Technology, ShanghaiTech University  |  Shanghai Institute of Microsystem and Information Technology, Chinese Academy of Sciences  |  University of Chinese Academy of Sciences

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. PIANO is the first parametric bone model of human hands from MRI data. 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, 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.

Input variables : MRI Images or RGB Images of Hand
Output Variables : Anatomical Bone Segmentation

Visit Model : github.com