← ArchivePaper2013
Anatomy Transfer
Ali-Hamadi Dicko, Tiantian Liu, Benjamin Gilles, Ladislav Kavan, Francois Faure, Olivier Palombi, Marie-Paule Cani
Transfers a full anatomical model (bones, muscles, fat) onto arbitrary character shapes, automating anatomy-based rig setup.
Abstract
Characters with precise internal anatomy are important in film and visual effects, as well as in medical applications. We propose the first semi-automatic method for creating anatomical structures, such as bones, muscles, viscera and fat tissues. This is done by transferring a reference anatomical model from an input template to an arbitrary target character, only defined by its boundary representation (skin). The fat distribution of the target character needs to be specified. We can either infer this information from MRI data, or allow the users to express their creative intent through a new editing tool. The rest of our method runs automatically: it first transfers the bones to the target character, while maintaining their structure as much as possible. The bone layer, along with the target skin eroded using the fat thickness information, are then used to define a volume where we map the internal anatomy of the source model using harmonic (Laplacian) deformation. This way, we are able to quickly generate anatomical models for a large range of target characters, while maintaining anatomical constraints.
How to read this
- Category
- Method: anatomy transfer for rig setup
- Contributions
- First semi-automatic method to create internal anatomy (bones, muscles, viscera, fat) by transferring a reference model to a target defined only by its skin
- Transfers bones while preserving their structure, then maps interior anatomy via harmonic (Laplacian) deformation into a volume bounded by skin and bone
- Drives the target fat distribution either from MRI data or from an interactive editing tool for creative control
- Context
- Extends anatomically based character modeling (Teran et al. Creating and Simulating Skeletal Muscle from the Visible Human Data Set) by automating anatomy setup onto arbitrary target shapes.Builds on: Creating and Simulating Skeletal Muscle from the Visible Human Data Set
- Correctness
- Demonstrated across a range of target characters while maintaining anatomical constraints; it is semi-automatic (fat distribution must be supplied) and transfer quality depends on correspondence between the template and a target that differs strongly in proportion.
- Clarity
- Accessible pipeline; a first pass conveys the transfer stages, a second pass is needed for the harmonic mapping and constraint handling.
- How to read it
- Focus on the bone-then-interior transfer stages and the fat-distribution input; a second pass on the Laplacian volume mapping pays off if you intend to set up anatomy-based rigs.
Built upon by
- Computational Bodybuilding: Anatomically-Based Modeling of Human Bodies 2015
- Reconstructing Personalized Anatomical Models for Physics-based Body Animation 2016
- Animatomy: An Animator-Centric, Anatomically Inspired System for 3D Facial Modeling, Animation and Transfer 2022
- TailorMe: Self-Supervised Learning of an Anatomically Constrained Volumetric Human Shape Model 2024
Related work
- Anatomically Based Modeling 1997 / SIGGRAPH
- Anatomy-Based Modeling of the Human Musculature 1997 / SIGGRAPH
- OSSO: Obtaining Skeletal Shape from Outside 2022 / CVPR
- Differentiable Simulation of Inertial Musculotendons 2022 / SIGGRAPH Asia
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 →