GEAR: GEometry-motion Alternating Refinement for Articulated Object Modeling with Gaussian Splatting

ArXi:2604.07728v1 Announce Type: new High-fidelity interactive digital assets are essential for embodied intelligence and robotic interaction, yet articulated objects remain challenging to reconstruct due to their complex structures and coupled geometry-motion relationships. Existing methods suffer from instability in geometry-motion joint optimization, while their generalization remains limited on complex multi-joint or out-of-distribution objects.