SPRig: Self-Supervised Pose-Invariant Rigging from Mesh Sequences
This addresses rigging inconsistencies in sequential data like animal motion capture or video-derived meshes, offering a domain-specific improvement.
The paper tackles the problem of rigging mesh sequences without a canonical rest pose, which causes topological inconsistencies in existing methods, and proposes SPRig, a fine-tuning framework that enforces cross-frame consistency losses to achieve state-of-the-art temporal stability and reduce artifacts.
State-of-the-art rigging methods assume a canonical rest pose--an assumption that fails for sequential data (e.g., animal motion capture or AIGC/video-derived mesh sequences) that lack the T-pose. Applied frame-by-frame, these methods are not pose-invariant and produce topological inconsistencies across frames. Thus We propose SPRig, a general fine-tuning framework that enforces cross-frame consistency losses to learn pose-invariant rigs on top of existing models. We validate our approach on rigging using a new permutation-invariant stability protocol. Experiments demonstrate SOTA temporal stability: our method produces coherent rigs from challenging sequences and dramatically reduces the artifacts that plague baseline methods. The code will be released publicly upon acceptance.