FreeArtGS: Articulated Gaussian Splatting Under Free-moving Scenario

TL;DR

FreeArtGS introduces a scalable, end-to-end method for reconstructing articulated objects from monocular RGB-D videos in free-moving scenarios, overcoming previous limitations of axis alignment and coverage.

Contribution

It presents a novel approach combining free-moving part segmentation, joint estimation, and optimization to reconstruct articulated objects without strict setup constraints.

Findings

Outperforms existing methods on benchmarks and real-world data

Successfully reconstructs geometry, textures, and joint parameters

Demonstrates high scalability and practical applicability

Abstract

The increasing demand for augmented reality and robotics is driving the need for articulated object reconstruction with high scalability. However, existing settings for reconstructing from discrete articulation states or casual monocular videos require non-trivial axis alignment or suffer from insufficient coverage, limiting their applicability. In this paper, we introduce FreeArtGS, a novel method for reconstructing articulated objects under free-moving scenario, a new setting with a simple setup and high scalability. FreeArtGS combines free-moving part segmentation with joint estimation and end-to-end optimization, taking only a monocular RGB-D video as input. By optimizing with the priors from off-the-shelf point-tracking and feature models, the free-moving part segmentation module identifies rigid parts from relative motion under unconstrained capture. The joint estimation module calibrates the unified object-to-camera poses and recovers joint type and axis robustly from part segmentation. Finally, 3DGS-based end-to-end optimization is implemented to jointly reconstruct visual textures, geometry, and joint angles of the articulated object. We conduct experiments on two benchmarks and real-world free-moving articulated objects. Experimental results demonstrate that FreeArtGS consistently excels in reconstructing free-moving articulated objects and remains highly competitive in previous reconstruction settings, proving itself a practical and effective solution for realistic asset generation. The project page is available at: https://freeartgs.github.io/