← ArchivePaper2022
NIMBLE: A Non-rigid Hand Model with Bones and Muscles
Yuwei Li, Longwen Zhang, Zesong Qiu, Yingwenqi Jiang, Nianyi Li, Yuexin Ma, Yuyao Zhang, Lan Xu, Jingyi Yu
Parametric hand model comprising 20 bone meshes and 7 tetrahedral muscle groups built from annotated MRI data, enabling anatomy-aware hand pose estimation.
Abstract
Emerging Metaverse applications demand reliable, accurate, and photorealistic reproductions of human hands to perform sophisticated operations as if in the physical world. While real human hand represents one of the most intricate coordination between bones, muscle, tendon, and skin, state-of-the-art techniques unanimously focus on modeling only the skeleton of the hand. In this paper, we present NIMBLE, a novel parametric hand model that includes the missing key components, bringing 3D hand model to a new level of realism. We first annotate muscles, bones and skins on the recent Magnetic Resonance Imaging hand (MRI-Hand) dataset [Li et al. 2021] and then register a volumetric template hand onto individual poses and subjects within the dataset. NIMBLE consists of 20 bones as triangular meshes, 7 muscle groups as tetrahedral meshes, and a skin mesh. Via iterative shape registration and parameter learning, it further produces shape blend shapes, pose blend shapes, and a joint regressor. We demonstrate applying NIMBLE to modeling, rendering, and visual inference tasks. By enforcing the inner bones and muscles to match anatomic and kinematic rules, NIMBLE can animate 3D hands to new poses at unprecedented realism. To model the appearance of skin, we further construct a photometric HandStage to acquire high-quality textures and normal maps to model wrinkles and palm print.
How to read this
- Category
- Method: anatomy-aware parametric hand model
- Contributions
- NIMBLE, a parametric hand model adding 20 bone meshes and 7 tetrahedral muscle groups beneath a skin mesh, beyond skeleton-only models
- Annotation of muscles, bones, and skin on an MRI-Hand dataset plus registration of a volumetric template across poses and subjects
- Learned shape and pose blend shapes and a joint regressor that enforce anatomic and kinematic rules for modeling, rendering, and inference
- Context
- Extends prior MRI-based hand modeling (e.g., Wang et al. 2019) by going from skeleton-only representations to a full bones-muscles-skin parametric model.Builds on: Hand Modeling and Simulation Using Stabilized Magnetic Resonance Imaging
- Correctness
- Built and registered from a specific MRI hand dataset, so realism is tied to that captured population and annotation quality, and animation plausibility depends on the enforced anatomic and kinematic constraints rather than full soft-tissue simulation.
- Clarity
- Accessible motivation; a first pass conveys the anatomy-aware idea, a second pass is needed for the registration and blend-shape learning details.
- How to read it
- Read first for what the model contains and how it differs from skeleton-only hands; do a second pass on the iterative registration and parameter learning if you intend to use or rebuild it.
Built upon by
Nothing yet.
Related work
- Data-Driven Physics for Human Soft Tissue Animation 2017 / SIGGRAPH
- BOSS: Bones, Organs and Skin Shape Model 2023 / arXiv
- Steklov-Poincare Skinning 2014 / SCA
- Hand Modeling and Simulation Using Stabilized Magnetic Resonance Imaging 2019 / SIGGRAPH
Keywords
This page summarises the entry and links to its original source. The archive never hosts or redistributes the publication itself.Show it in the full archive list →