ViP-Rig: Visual-Prompted Controllable Rigging

2026-07-30

AI Summary

Existing automatic rigging methods struggle to provide task-oriented, explicit control over skeletal structure and deformation behavior. To address this limitation, this work proposes ViP-Rig, a novel framework that enables end-to-end controllable rigging guided by visual prompts for the first time. Users specify 2D skeletal layouts and stiffness hint maps to steer a two-stage pipeline: first generating a controllable skeleton, then predicting skinning weights. The approach leverages a frozen pre-trained autoregressive generator and a skinning backbone, enhanced with gated adapters and a dense-to-compact visual prompt encoding mechanism to inject guidance features—eliminating the need for fine-tuning while supporting prompt-prioritized rigging and result-guided editing. Evaluated zero-shot on Articulation-XL2.0 and ModelsResource, ViP-Rig surpasses geometry-conditioned baselines in both skeleton and skinning weight recovery accuracy and demonstrates superior local controllability.

Abstract

Rigging is inherently task-dependent because the same mesh may require different skeletons and deformation behaviors across animation tasks. In practice, artists often inspect an initial rig and repeatedly edit its skeletal structure and deformation behavior to meet specific animation requirements. Existing automatic methods primarily generate a plausible rig from geometry, offering limited explicit control over the resulting skeleton and deformation behavior. In this work, we present ViP-Rig, a visual-prompted framework that supports both prompt-first rigging and result-guided editing by injecting features extracted from user-drawn or edited 2D skeletal and rigidity prompts into frozen pretrained backbones. Specifically, ViP-Rig consists of two stages, Skeleton Generation and Skinning Prediction. In the first stage, the skeletal sketch is processed by the Dense-to-Compact Visual Prompt Encoding to produce compact, fixed-length conditioning tokens. The resulting tokens are injected into a frozen pretrained autoregressive generator through gated adapters to control joint placement and branching structure while preserving the generator's geometric prior. In the second stage, the rigidity map is processed using the same visual encoding design, while the pretrained skinning backbone remains frozen. The resulting tokens are symmetrically injected into the point and joint streams to modulate point-joint compatibility and the resulting skinning weights. Experiments on Articulation-XL2.0 and zero-shot evaluation on ModelsResource show that ViP-Rig more accurately recovers target skeletons and skinning weights than geometry-conditioned baselines under prompt-guided evaluation. Qualitative results further demonstrate explicit and localized control in both prompt-first rigging and result-guided editing.

Problem

• rigging
• skeleton control
• deformation behavior
• visual prompting
• animation tasks

Innovation

• visual prompting
• controllable rigging
• skeleton generation
• skinning prediction
• frozen pretrained backbone