← ArchivePaper2022

SkinMixer: Blending 3D Animated Models

Stefano Nuvoli, Nico Pietroni, Paolo Cignoni, Riccardo Scateni, Marco Tarini

SIGGRAPH AsiaAcademic8 citesRigging Skinning

Composes new rigged and skinned characters by mixing body parts from production-ready animated models.

Open the paper ↗Trace in the lineage graph

Abstract

We propose a novel technique to compose new 3D animated models, such as videogame characters, by combining pieces from existing ones. Our method works on production-ready rigged, skinned, and animated 3D models to reassemble new ones. We exploit mix-and-match operations on the skeletons to trigger the automatic creation of a new mesh, linked to the new skeleton by a set of skinning weights and complete with a set of animations. The resulting model preserves the quality of the input meshings (which can be quad-dominant and semi-regular), skinning weights (inducing believable deformation), and animations, featuring coherent movements of the new skeleton. Our method enables content creators to reuse valuable, carefully designed assets by assembling new ready-to-use characters while preserving most of the hand-crafted subtleties of models authored by digital artists. As shown in the accompanying video, it allows for drastically cutting the time needed to obtain the final result.

How to read this

Category: Method: mix-and-match composition of rigged characters
Contributions: A technique to compose new animated 3D models by combining parts of existing production-ready rigged, skinned, animated assets
Mix-and-match operations on skeletons that automatically trigger creation of a new mesh, skinning weights, and animations
Preserves input meshing quality (quad-dominant, semi-regular), believable skinning deformation, and coherent skeleton motion
Context: Builds on the tradition of automatic rigging and skinning of 3D characters (Baran and Popovic, Automatic Rigging and Animation of 3D Characters, 2007), reframing it as reuse and recombination of already-authored assets.Builds on: Automatic Rigging and Animation of 3D Characters
Correctness: Demonstrated on videogame-style rigged characters in the accompanying video; results depend on the inputs being well-authored and structurally compatible, so seams, weight, and animation coherence at the joins are the things to scrutinize.
Clarity: Fairly accessible; a first pass conveys the operations and intent, with a second pass for the mesh-stitching and weight-transfer details.
How to read it: Read once for the skeleton-driven workflow and what is automated; second pass on the mesh blending and skinning-weight transfer at boundaries, and watch the video to judge deformation quality.

Builds on

Automatic Rigging and Animation of 3D Characters 2007

Built upon by

Nothing yet.

Related work

Geodesic Voxel Binding for Production Character Meshes 2013 / SCA
Animation Setup Transfer for 3D Characters 2016 / CGF
Real-Time Skeletal Skinning with Optimized Centers of Rotation 2016 / SIGGRAPH
NeuroSkinning: Automatic Skin Binding for Production Characters with Deep Graph Networks 2019 / SIGGRAPH

Keywords

model composition skinning weights linear blend skinning dual quaternion skinning skeleton animation retargeting bone-to-bone mapping signed distance function generalized winding number quad-dominant mesh semi-regular meshing keyframe animation mix-and-match implicit surface blending character rigging mesh fusion voxelization

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 →