OmniFaceRig: Fully Automatic Inner-Mouth-Aware Face Rigging Across Diverse 3D Character Topologies

2026-06-06

AI Summary

This work addresses the inefficiency of existing 3D facial rigging pipelines for characters across diverse topologies—including humans and various animals—due to their heavy reliance on manual intervention such as hand-labeled annotations, template adjustments, and oral structure placement. To overcome this limitation, we propose the first fully automatic, end-to-end framework that generates animation-ready rigs from a single static surface mesh, complete with FACS-based expressions, procedural teeth/gums/tongue geometry, and reparameterized UVs. Our approach integrates vision-language models and computer vision techniques to enable bindability assessment, multi-model face parsing, dense landmark-driven registration, and collision-aware expression transfer—all without manual labels or templates. We contribute an open benchmark, Omni-Bench, comprising 1,000 characters, on which our method achieves high rigging success rates, near-perfect facial segmentation recall, and low oral penetration, significantly advancing cross-species facial animation automation.

Abstract

Facial rigging - creating FACS-based blendshapes together with inner-mouth geometry (teeth, gums, and tongue) - remains a major bottleneck in 3D character production. Existing pipelines still require substantial designer effort, especially for manual landmark annotation, per-character template adjustment, and inner-mouth placement. We present OmniFaceRig, a fully automatic end-to-end pipeline that converts a static surface-only 3D character mesh, with no pre-modeled oral cavity, into an inner-mouth-aware FACS rig with up to 155 blendshapes, procedurally fitted teeth, gums, and tongue, and re-packed UV/texture. OmniFaceRig supports diverse topologies - humans, humanoids, long-muzzled animals (e.g., dogs, wolves, foxes), and short-muzzled animals (e.g., cats, bears, rabbits, tigers) - with no manual landmarks, no user-provided templates, and no per-asset setup. The pipeline combines hybrid VLM+CV riggability checking, multi-model face parsing, dense keypoint-driven template registration, procedural inner-mouth construction, and collision-aware blendshape transfer. For non-human characters, OmniFaceRig selects topology-specific face and inner-mouth templates and uses collision-aware inner-mouth fitting to reduce teeth-face intersections without exposing users to category-specific tuning. We also publicly release Omni-Bench, a freely available benchmark dataset of 1,000 biped 3D characters with FACS facial blendshapes and inner-mouth geometry, spanning humans, humanoids, cats, dogs, and other animals. Experiments show high final rigging success on screened Omni-Bench inputs, nearly complete face detection recall from the segmentation ensemble and reliable inner-mouth placement with low penetration. Together, OmniFaceRig provides an automatic path from static generated characters to animation-ready facial rigs across both human and non-human topologies.

Problem

• facial rigging
• FACS blendshapes
• inner-mouth geometry
• 3D character
• automatic rigging

Innovation

• automatic face rigging
• inner-mouth modeling
• FACS blendshapes
• cross-topology generalization
• collision-aware transfer