LAGA：通过 Gaussian Splatting 实现分层 3D 化身生成与定制
LAGA: Layered 3D Avatar Generation and Customization via Gaussian Splatting
AI总结：
提出分层 Gaussian 化身框架 LAGA，通过分层 Gaussian 表示、由粗到细服装生成、dual-SDS 与正则化损失实现服装级编辑和跨化身迁移。
摘要：
从文本描述创建并定制 3D 着装化身是一项关键且具有挑战性的任务。传统方法通常将人体和服装视为不可分割的整体，限制了用户自由混搭服装的能力。针对这一局限，我们提出了 LAyered Gaussian Avatar（LAGA），这是一个精心设计的框架，能够创建具有多样服装的高保真可分解化身。通过将服装与化身解耦，我们的框架使用户能够方便地在服装层面编辑化身。我们的方法首先使用一组以分层结构组织的 Gaussian 点对化身进行建模，其中每一层对应一件特定服装或人体本身。为了给每一层生成高质量服装，我们引入了一种用于多样服装生成的由粗到细策略，以及一种新颖的 dual-SDS 损失函数，以保持所生成服装与化身组件（包括人体和其他服装）之间的一致性。此外，我们引入了三个正则化损失来引导 Gaussian 的运动以实现服装迁移，使服装能够自由迁移到各种化身。大量实验表明，我们的方法在 3D 着装人体生成方面优于现有方法。
英文摘要：
Creating and customizing a 3D clothed avatar from textual descriptions is a critical and challenging task. Traditional methods often treat the human body and clothing as inseparable, limiting users' ability to freely mix and match garments. In response to this limitation, we present LAyered Gaussian Avatar (LAGA), a carefully designed framework enabling the creation of high-fidelity decomposable avatars with diverse garments. By decoupling garments from avatar, our framework empowers users to conviniently edit avatars at the garment level. Our approach begins by modeling the avatar using a set of Gaussian points organized in a layered structure, where each layer corresponds to a specific garment or the human body itself. To generate high-quality garments for each layer, we introduce a coarse-to-fine strategy for diverse garment generation and a novel dual-SDS loss function to maintain coherence between the generated garments and avatar components, including the human body and other garments. Moreover, we introduce three regularization losses to guide the movement of Gaussians for garment transfer, allowing garments to be freely transferred to various avatars. Extensive experimentation demonstrates that our approach surpasses existing methods in the generation of 3D clothed humans.
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。
