AI RESEARCH

SPRig: Self-Supervised Pose-Invariant Rigging from Mesh Sequences

arXiv CS.CV

ArXi:2602.12740v2 Announce Type: replace State-of-the-art rigging methods typically assume a predefined canonical rest pose. However, this assumption does not hold for dynamic mesh sequences such as DyMesh or DT4D, where no canonical T-pose is available. When applied independently frame-by-frame, existing methods lack pose invariance and often yield temporally inconsistent topologies.