Deep learning has demonstrated remarkable capabilities in simulating complex dynamic systems. However, existing methods require known physical properties as supervision or inputs, limiting their applicability under unknown conditions. To explore this challenge, we introduce Cloth Dynamics Grounding (CDG), a novel scenario for unsupervised learning of cloth dynamics from multi-view visual observations. We further propose Cloth Dynamics Splatting (CloDS), an unsupervised dynamic learning framework designed for CDG. CloDS adopts a three-stage pipeline that first performs video-to-geometry grounding and then trains a dynamics model on the grounded meshes. To cope with large non-linear deformations and severe self-occlusions during grounding, we introduce a dual-position opacity modulation that supports bidirectional mapping between 2D observations and 3D geometry via mesh-based Gaussian splatting in video-to-geometry grounding stage. It jointly considers the absolute and relative position of Gaussian components. Comprehensive experimental evaluations demonstrate that CloDS effectively learns cloth dynamics from visual data while maintaining strong generalization capabilities for unseen configurations. Our code is available at https://github.com/whynot-zyl/CloDS. Visualization results are available at https://github.com/whynot-zyl/CloDS_video}.%\footnote{As in this example.

翻译：深度学习在模拟复杂动态系统方面已展现出卓越能力。然而，现有方法需要已知物理属性作为监督或输入，限制了其在未知条件下的适用性。为探索这一挑战，我们提出了布料动态建模（CDG）这一新颖场景，旨在从多视角视觉观测中无监督学习布料动力学。我们进一步提出了布料动态溅射（CloDS），这是一个专为CDG设计的无监督动态学习框架。CloDS采用三阶段流程：首先执行视频到几何的建模，随后在建模得到的网格上训练动力学模型。为应对建模过程中巨大的非线性形变和严重自遮挡问题，我们在视频到几何建模阶段引入了双位置不透明度调制机制，通过基于网格的高斯溅射实现二维观测与三维几何之间的双向映射。该机制同时考虑了高斯分量的绝对位置与相对位置。综合实验评估表明，CloDS能有效从视觉数据中学习布料动力学，同时对未见配置保持强大的泛化能力。代码发布于https://github.com/whynot-zyl/CloDS，可视化结果详见https://github.com/whynot-zyl/CloDS_video。