Reconstructing and simulating elastic objects from visual observations is crucial for applications in computer vision and robotics. Existing methods, such as 3D Gaussians, model 3D appearance and geometry, but lack the ability to estimate physical properties for objects and simulate them. The core challenge lies in integrating an expressive yet efficient physical dynamics model. We propose Spring-Gaus, a 3D physical object representation for reconstructing and simulating elastic objects from videos of the object from multiple viewpoints. In particular, we develop and integrate a 3D Spring-Mass model into 3D Gaussian kernels, enabling the reconstruction of the visual appearance, shape, and physical dynamics of the object. Our approach enables future prediction and simulation under various initial states and environmental properties. We evaluate Spring-Gaus on both synthetic and real-world datasets, demonstrating accurate reconstruction and simulation of elastic objects. Project page: https://zlicheng.com/spring_gaus/.

翻译：从视觉观测中重建与仿真弹性物体对于计算机视觉与机器人学应用至关重要。现有方法（如三维高斯模型）能够建模三维外观与几何，但缺乏估计物体物理属性并进行仿真的能力。核心挑战在于集成一种表达能力强且高效的计算动力学模型。我们提出 Spring-Gaus，一种用于从多视角物体视频中重建与仿真弹性物体的三维物理对象表示方法。具体而言，我们开发并将三维弹簧质点模型集成到三维高斯核中，从而能够同时重建物体的视觉外观、形状与物理动力学特性。我们的方法支持在不同初始状态与环境属性下进行未来状态预测与仿真。我们在合成数据集与真实世界数据集上评估了 Spring-Gaus，验证了其对弹性物体进行精确重建与仿真的能力。项目页面：https://zlicheng.com/spring_gaus/。