aiqbench analysis
This research advances 3D reconstruction by integrating structural constraints into Gaussian Splatting to accurately model articulated objects with moving parts. By disentangling geometry from motion through explicit spatial coherence and connectivity losses, the method overcomes common limitations in part decomposition found in photometric-only approaches. The work represents a significant step forward for machine learning applications requiring high-fidelity 3D understanding of complex mechanical systems.
StructureGS: Structure-aware Gaussian Splatting for Articulated Object Reconstruction
arXiv:2607.26889v1 Announce Type: cross 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.
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.
Graphics (cs.GR); Computer Vision and Pattern Recognition (cs.CV); Robotics (cs.RO)
arXiv:2607.26889 [cs.GR]
(or arXiv:2607.26889v1 [cs.GR] for this version)
https://doi.org/10.48550/arXiv.2607.26889 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 264 words
Related coverage
RORA: Realistic Object Reconstruction with Articulation
arXiv · Aug 6, 2026
CoGeo-GS: Concept-Driven and Geometry-Aware Multi-Object Removal in 3D Scenes
arXiv · Aug 28, 2026
Return-to-Home Feasible Micro-Aerial Vehicle Exploration for 3D Gaussian Splatting Reconstruction
arXiv · Oct 6, 2026
Posterior Variance Is a Constraint Map, Not an Error Map: Closed-Form Uncertainty for Radiative Gaussian Splatting in Sparse-View CT
arXiv · Aug 4, 2026