SPAGS：基于单一状态的稀疏视角关节物体重建（通过平面高斯溅射）
SPAGS: Sparse-View Articulated Object Reconstruction from Single State via Planar Gaussian Splatting
AI总结：
本文提出一种无需多视角观测的关节物体重建方法，通过平面高斯溅射实现稀疏视角下的高精度重建，结合视觉-语言模型实现开放词汇部分分割与参数估计。
摘要：
关节物体在日常环境中普遍存在，其3D重建在多个领域具有重要意义。然而，现有方法通常需要多阶段、多视角的高成本输入。为解决这一问题，本文提出一种类别无关的关节物体重建框架，仅使用单状态下的稀疏视角RGB图像。首先引入高斯信息场以感知候选相机姿态下的最优稀疏视角。为确保几何精度，将传统3D高斯转换为平面基元，以实现准确的法线和深度估计。平面高斯随后以粗到细的方式优化，通过深度平滑性和少量样本扩散先验进行正则化。此外，利用视觉-语言模型（VLM）通过视觉提示实现开放词汇部分分割和联合参数估计。在合成和现实数据集上的大量实验表明，本文方法显著优于现有基线，实现了更优的部分级表面重建精度。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
