FreeArtGS: Articulated Gaussian Splatting Under Free-moving Scenario

2026-03-23

AI Summary

This work proposes FreeArtGS, a novel method that enables end-to-end articulated object reconstruction under fully free-motion conditions using only a monocular RGB-D video. Existing approaches are limited by their reliance on discrete joint states or unstructured monocular videos, making them ill-suited for freely moving scenarios. FreeArtGS overcomes these limitations by jointly optimizing unconstrained motion segmentation, joint type classification, and axis parameter estimation, while integrating 3D Gaussian Splatting to co-optimize geometry, texture, and joint angles in a unified framework. Evaluated on multiple benchmarks and real-world free-motion datasets, FreeArtGS significantly outperforms state-of-the-art methods, demonstrating competitive performance even under conventional settings. The approach exhibits high scalability and practical utility, marking a substantial advance in dynamic articulated object reconstruction.

Technology Category

• Computer Vision: Motion & Tracking
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Machine Learning: Learning with Manifolds

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Responsible Web: Machine-in-the-loop, human agency and autonomy

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/

Problem

• articulated object reconstruction
• free-moving scenario
• monocular video
• joint estimation
• scalability

Innovation

• Articulated Object Reconstruction
• Free-moving Scenario
• Gaussian Splatting
• Joint Estimation
• Monocular RGB-D Video