Auto-Connect: Connectivity-Preserving RigFormer with Direct Preference Optimization

2025-06-13

AI Summary

To address topology distortion and skinning artifacts in automatic skeletal rigging, this paper proposes RigFormer. First, it introduces a connectivity-preserving hierarchical joint tokenization mechanism that explicitly encodes anatomical connectivity constraints. Second, it designs a topology-aware reward function and integrates it with Direct Preference Optimization (DPO) for end-to-end fine-tuning to enhance structural plausibility. Third, it employs implicit geodesic distance encoding to guide top-k bone selection, enabling high-fidelity vertex skinning. The three core contributions—(1) the first connectivity-aware joint tokenization scheme, (2) a topology-reward-guided DPO paradigm for rig optimization, and (3) an implicit geodesic feature-driven skinning strategy—collectively improve skeletal topology accuracy and anatomical consistency. RigFormer achieves state-of-the-art performance in deformation quality and structural robustness on standard benchmarks.

Technology Category

• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning
• Intelligent Robots: Embodied AI
• Computer Vision: Diffusion Models for Vision

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Search and Retrieval-Augmented AI: Agentic search

Abstract

We introduce Auto-Connect, a novel approach for automatic rigging that explicitly preserves skeletal connectivity through a connectivity-preserving tokenization scheme. Unlike previous methods that predict bone positions represented as two joints or first predict points before determining connectivity, our method employs special tokens to define endpoints for each joint's children and for each hierarchical layer, effectively automating connectivity relationships. This approach significantly enhances topological accuracy by integrating connectivity information directly into the prediction framework. To further guarantee high-quality topology, we implement a topology-aware reward function that quantifies topological correctness, which is then utilized in a post-training phase through reward-guided Direct Preference Optimization. Additionally, we incorporate implicit geodesic features for latent top-k bone selection, which substantially improves skinning quality. By leveraging geodesic distance information within the model's latent space, our approach intelligently determines the most influential bones for each vertex, effectively mitigating common skinning artifacts. This combination of connectivity-preserving tokenization, reward-guided fine-tuning, and geodesic-aware bone selection enables our model to consistently generate more anatomically plausible skeletal structures with superior deformation properties.

Problem

• Preserves skeletal connectivity in automatic rigging
• Ensures topological accuracy via connectivity-aware prediction
• Improves skinning quality using geodesic bone selection

Innovation

• Connectivity-preserving tokenization for joint hierarchy
• Topology-aware reward-guided Direct Preference Optimization
• Geodesic-aware latent top-k bone selection