We present a novel solution to the garment animation problem through deep learning. Our contribution allows animating any template outfit with arbitrary topology and geometric complexity. Recent works develop models for garment edition, resizing and animation at the same time by leveraging the support body model (encoding garments as body homotopies). This leads to complex engineering solutions that suffer from scalability, applicability and compatibility. By limiting our scope to garment animation only, we are able to propose a simple model that can animate any outfit, independently of its topology, vertex order or connectivity. Our proposed architecture maps outfits to animated 3D models into the standard format for 3D animation (blend weights and blend shapes matrices), automatically providing of compatibility with any graphics engine. We also propose a methodology to complement supervised learning with an unsupervised physically based learning that implicitly solves collisions and enhances cloth quality.
翻译:我们通过深层学习提出了服装动画问题的新解决方案。 我们的贡献使我们得以动画任何带有任意地形学和几何复杂性的模板。 最近的工作通过利用支持体模型(将服装编码成身体同质体),同时开发了服装版、重新调整和动画模型。 这导致复杂的工程解决方案,这些解决方案有可缩放性、可应用性和兼容性。 通过将我们的范围仅限于服装动画,我们能够提出一个简单的模型,可以将任何设备与地形学、顶端顺序或连通性不相干。 我们拟议的建筑图绘制了3D动画标准格式中的3D动画模型的装饰物(骨质重量和混合形状矩阵),自动提供与任何图形引擎的兼容性。 我们还提出了一种方法,用以辅助监督性学习,同时采用非超强的物理学习,不言明地解决碰撞,提高布质。