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

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 depend on substantial designer effort: inner-mouth components are commonly placed by hand, and landmark annotation and per-character template adjustments are routine. 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, including humans, humanoids, long-muzzled animals (elongated snouts; e.g., dogs, wolves, foxes), and short-muzzled animals (compact or nearly absent snouts; e.g., cats, bears, rabbits, tigers), with no manual landmarks, no user-provided templates, and no per-asset template setup. OmniFaceRig combines a VLM+CV riggability checker, a four-model face detection and segmentation ensemble (face landmark detection, Sapiens, SAM 3, and fine-tuned Sapiens), dense keypoint-driven template registration, procedural inner-mouth construction, and collision-aware blendshape transfer. To handle non-human characters, it automatically selects from a small library of topology-specific templates with a nose-landmark-free design and uses ARAP+SDF-based inner-mouth fitting to reduce teeth-face intersections. We also introduce Omni-Bench , an open-source benchmark of 1,000 biped 3D characters rigged with FACS facial blendshapes and inner-mouth geometry, spanning realistic and humanoid humans, cats, dogs, and other animals. Experiments show high final rigging success on screened Omni-Bench evaluation inputs, nearly complete face detection recall from the segmentation ensemble, reliable inner-mouth placement with low penetration, and 20–30 s end-to-end latency on a single A100 GPU including data I/O. Together, OmniFaceRig provides an automatic path from static generated characters to animation-ready facial rigs across both human and non-human topologies. Additional results, videos, and resources are available on our Project Page: https://omnifacerig.github.io/.