PIANO: A Parametric Hand Bone Model from Magnetic Resonance Imaging (2021-06-21T00:00:00.000000Z)

TL;DR

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

Abstract

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.

Authors

Minye Wu

2 papers

Jingyi Yu

6 papers

Lan Xu

4 papers

TL;DR

Abstract

Authors

References29 items

SMPL: A Skinned Multi-Person Linear Model

FlyFusion: Realtime Dynamic Scene Reconstruction Using a Flying Depth Camera

Estimation of Finite Finger Joint Centers of Rotation Using 3D Hand Skeleton Motions Reconstructed from CT Scans

Constraining dense hand surface tracking with elasticity

DeepHandMesh: A Weakly-supervised Deep Encoder-Decoder Framework for High-fidelity Hand Mesh Modeling

KiU-Net: Towards Accurate Segmentation of Biomedical Images using Over-complete Representations

FreiHAND: A Dataset for Markerless Capture of Hand Pose and Shape From Single RGB Images

Hand modeling and simulation using stabilized magnetic resonance imaging

Fetal Pose Estimation in Volumetric MRI using a 3D Convolution Neural Network

Learning Joint Reconstruction of Hands and Manipulated Objects

A musculoskeletal model of the hand and wrist: model definition and evaluation

An Articulating Statistical Shape Model of the Human Hand

3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation

V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation

Automatic Segmentation of Wrist Bones in CT Using a Statistical Wrist Shape $+$ Pose Model

Automatic articulated registration of hand radiographs

Soft-Tissue Deformation for In Vivo Volume Animation

Finger joint kinematics from MR images

Proceedings of the 2005 ACM SIGGRAPH/Eurographics symposium on Computer animation

Modeling deformable human hands from medical images

Marching cubes: A high resolution 3D surface construction algorithm

HTML: A Parametric Hand Texture Model for 3D Hand Reconstruction and Personalization

Rgb2hands: real-time tracking of 3d hand interactions from monocular rgb video

ACM Transactions on Graphics (TOG)

Embodied Hands : Modeling and Capturing Hands and Bodies Together * * Supplementary Material * *

In 15th Pacific Conference on Computer Graphics and Applications (PG’07)

In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Puerto Rico June pages Ego Motion Estimation Using Optical Flow Fields Observed from Multiple Cameras

A 3 D METHOD FOR SEGMENTING AND REGISTERING CARPAL BONES FROM CT VOLUME IMAGES

[On the physiology of joints].

Field of Study

Journal Information

Name

Volume

Venue Information

Name

Type

URL

Alternate Names