We introduce Gaussian Wardrobe, a novel framework to digitalize compositional 3D neural avatars from multi-view videos. Existing methods for 3D neural avatars typically treat the human body and clothing as an inseparable entity. However, this paradigm fails to capture the dynamics of complex free-form garments and limits the reuse of clothing across different individuals. To overcome these problems, we develop a novel, compositional 3D Gaussian representation to build avatars from multiple layers of free-form garments. The core of our method is decomposing neural avatars into bodies and layers of shape-agnostic neural garments. To achieve this, our framework learns to disentangle each garment layer from multi-view videos and canonicalizes it into a shape-independent space. In experiments, our method models photorealistic avatars with high-fidelity dynamics, achieving new state-of-the-art performance on novel pose synthesis benchmarks. In addition, we demonstrate that the learned compositional garments contribute to a versatile digital wardrobe, enabling a practical virtual try-on application where clothing can be freely transferred to new subjects. Project page: https://ait.ethz.ch/gaussianwardrobe

翻译：我们提出了高斯衣橱，一种从多视角视频数字化构建可组合3D神经化身的创新框架。现有的3D神经化身方法通常将人体与服装视为不可分割的整体。然而，这种范式难以捕捉复杂自由形式服装的动态特性，并限制了服装在不同个体间的重复使用。为解决这些问题，我们开发了一种新颖的可组合3D高斯表示方法，通过多层自由形式服装构建化身。我们方法的核心在于将神经化身分解为身体与多层形状无关的神经服装。为实现这一目标，我们的框架从多视角视频中学习解耦每层服装，并将其规范化为形状无关空间。在实验中，我们的方法能够建模具有高保真动态效果的逼真化身，在新姿态合成基准测试中取得了最先进的性能。此外，我们证明了所学习的可组合服装可构成多功能数字衣橱，实现实用的虚拟试穿应用——服装能够自由迁移至新主体。项目页面：https://ait.ethz.ch/gaussianwardrobe