StructureGS: Structure-aware Gaussian Splatting for Articulated Object Reconstruction

2026-07-29

AI Summary

This work addresses the ambiguity in part decomposition and geometric artifacts arising from the coupling of geometry, appearance, and motion parameters in reconstructing articulated objects. It introduces explicit structural constraints into the 3D Gaussian Splatting framework for the first time. By leveraging oriented bounding boxes to enforce spatial consistency and jointly optimizing with a structural connectivity loss and photometric supervision, the method effectively decouples geometric and motion representations. This approach significantly enhances part boundary sharpness and physical plausibility, achieving state-of-the-art performance on articulated object datasets and producing high-quality reconstructions with accurate geometry and coherent structure.

Abstract

Reconstructing articulated objects with multiple movable parts is essential for understanding object structure and enabling physical interaction. However, this reconstruction task poses significant challenges due to the entanglement of geometry, appearance, and motion parameters during optimization. Existing methods rely primarily on photometric supervision, which commonly fails to disentangle these interdependent components, resulting in poor part decomposition with blurred boundaries and geometric artifacts. To address this limitation, we introduce StructureGS, a reconstruction framework for articulated objects that integrates structure-aware guidance into 3D Gaussian Splatting. Our approach leverages oriented bounding boxes of object parts to enforce two key structural properties: spatial coherence, which constrains each part's geometry to remain compact and spatially coherent within its designated region, and structural connectivity, which enforces physically plausible contact relationships between adjacent parts. These properties are realized through structure-aware losses that inject explicit structural constraints into the optimization process. Extensive experiments demonstrate that our method achieves state-of-the-art performance in articulated object reconstruction, producing high-quality results with well-defined part geometries.

Problem

• articulated object reconstruction
• geometry-appearance-motion entanglement
• part decomposition
• structural disentanglement
• 3D reconstruction

Innovation

• Structure-aware Gaussian Splatting
• Articulated Object Reconstruction
• Spatial Coherence
• Structural Connectivity
• Oriented Bounding Boxes