GEAR: GEometry-motion Alternating Refinement for Articulated Object Modeling with Gaussian Splatting
This addresses the problem of creating high-fidelity interactive digital assets for embodied intelligence and robotic interaction, representing an incremental improvement over existing methods.
The paper tackles the challenge of reconstructing articulated objects with complex structures by proposing GEAR, an alternating optimization framework that jointly models geometry and motion using Gaussian Splatting, achieving state-of-the-art results in geometric reconstruction and motion parameter estimation on multiple benchmarks.
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. To address these challenges, we propose GEAR, an EM-style alternating optimization framework that jointly models geometry and motion as interdependent components within a Gaussian Splatting representation. GEAR treats part segmentation as a latent variable and joint motion parameters as explicit variables, alternately refining them for improved convergence and geometric-motion consistency. To enhance part segmentation quality without sacrificing generalization, we leverage a vanilla 2D segmentation model to provide multi-view part priors, and employ a weakly supervised constraint to regularize the latent variable. Experiments on multiple benchmarks and our newly constructed dataset GEAR-Multi demonstrate that GEAR achieves state-of-the-art results in geometric reconstruction and motion parameters estimation, particularly on complex articulated objects with multiple movable parts.