SPAGS: Sparse-View Articulated Object Reconstruction from Single State via Planar Gaussian Splatting

TL;DR

This paper introduces SPAGS, a novel framework for reconstructing articulated objects from sparse-view RGB images using planar Gaussian splatting, enabling accurate 3D reconstruction with minimal inputs.

Contribution

The method employs a Gaussian information field and planar Gaussian primitives, combined with vision-language models, to achieve category-agnostic, high-fidelity articulated object reconstruction from single-state sparse views.

Findings

Outperforms existing methods on synthetic and real datasets.

Achieves superior part-level surface reconstruction fidelity.

Enables open-vocabulary part segmentation and joint parameter estimation.

Abstract

Articulated objects are ubiquitous in daily environments, and their 3D reconstruction holds great significance across various fields. However, existing articulated object reconstruction methods typically require costly inputs such as multi-stage and multi-view observations. To address the limitations, we propose a category-agnostic articulated object reconstruction framework via planar Gaussian Splatting, which only uses sparse-view RGB images from a single state. Specifically, we first introduce a Gaussian information field to perceive the optimal sparse viewpoints from candidate camera poses. To ensure precise geometric fidelity, we constrain traditional 3D Gaussians into planar primitives, facilitating accurate normal and depth estimation. The planar Gaussians are then optimized in a coarse-to-fine manner, regularized by depth smoothness and few-shot diffusion priors. Furthermore, we leverage a Vision-Language Model (VLM) via visual prompting to achieve open-vocabulary part segmentation and joint parameter estimation. Extensive experiments on both synthetic and real-world datasets demonstrate that our approach significantly outperforms existing baselines, achieving superior part-level surface reconstruction fidelity.