A Geodesic Cut-Cell Prior for Neural Skinning

2026-08-11

AI Summary

Existing data-driven skinning weight methods suffer from limited generalization and struggle to balance geometric plausibility with animation quality. This work proposes “Cut-Cell Skinning,” a novel geometric prior based on an approximation of geodesic distance fields, which for the first time integrates efficient graph-based geodesic distance computation into neural skinning learning. This approach significantly enhances model robustness and training efficiency on in-the-wild meshes while avoiding the topological limitations inherent in traditional cage- or voxel-based methods. The proposed prior seamlessly integrates into diverse neural skinning architectures, consistently improving performance across multiple benchmarks to achieve state-of-the-art results, and enables inference speeds orders of magnitude faster than conventional optimization-based solvers.

Abstract

We introduce cut-cell skinning, a geometric prior designed to augment data-driven skinning weight generation. While data-driven methods show promise in producing high-quality skinning weights, they often lack the generalizability of classic geometric approaches. To bridge this gap, we propose a geometric prior that can be robustly computed for in-the-wild meshes and is efficient for large-scale machine learning workflows. The key idea of our cut-cell skinning is a fast graph-based approximation of the volumetric geodesics distances, motivated by their importance in classic skinning weight computation. Our method achieves orders of magnitude speedup compared to optimization-based solvers and remains resilient to topological artifacts common in cage- or voxel-based alternatives. We demonstrate the efficacy of the cut-cell skinning prior by integrating it into recent neural skinning models, showing consistent improvements across existing methods and achieving state-of-the-art results. Project page: https://wenchao-m.github.io/CutCell.github.io/

Problem

• skinning weights
• geometric prior
• generalizability
• in-the-wild meshes
• data-driven skinning

Innovation

• geodesic distance
• cut-cell skinning
• neural skinning
• geometric prior
• graph-based approximation