分离人体与衣物的高斯渲染方法，实现逼真布料动态重建。
CLOTH-HUGS: Cloth Aware Human Gaussian Splatting
- 用独立高斯层分别表示人体和衣物，共享统一空间建模
- 在多个数据集上降低28% LPIPS，提升布料形变一致性
- 适合需要真实布料动画的虚拟试衣、影视特效场景
我们提出 Cloth-HUGS，一种基于高斯溅射的神经渲染框架，用于逼真着装人体重建，能显式分离身体与衣物。与以往将衣物融入单一身体表示并难以处理松散衣物和复杂形变的方法不同，Cloth-HUGS 在共享规范空间中使用独立的高斯层表示表演者的人体与衣物。该规范体积联合编码身体、衣物和场景基元，并通过 SMPL 驱动的运动学结构结合学习到的线性混合皮肤权重进行变形。为提升布料真实感，从网格拓扑初始化衣物高斯，并引入仿真一致性、ARAP 正则化及掩码监督等物理启发约束。此外，我们设计了深度感知多遍渲染策略，实现稳定的身体-衣物-场景合成，支持超过 60 FPS 的实时渲染。在多个基准测试中，Cloth-HUGS 在感知质量和几何保真度上均优于当前最优方法，LPIPS 最多降低 28%，同时生成时序一致的衣物动态。
原文摘要 · Abstract (English)
We present Cloth-HUGS, a Gaussian Splatting based neural rendering framework for photorealistic clothed human reconstruction that explicitly disentangles body and clothing. Unlike prior methods that absorb clothing into a single body representation and struggle with loose garments and complex deformations, Cloth-HUGS represents the performer using separate Gaussian layers for body and cloth within a shared canonical space. The canonical volume jointly encodes body, cloth, and scene primitives and is deformed through SMPL-driven articulation with learned linear blend skinning weights. To improve cloth realism, we initialize cloth Gaussians from mesh topology and apply physics-inspired constraints, including simulation-consistency, ARAP regularization, and mask supervision. We further introduce a depth-aware multi-pass rendering strategy for robust body-cloth-scene compositing, enabling real-time rendering at over 60 FPS. Experiments on multiple benchmarks show that Cloth-HUGS improves perceptual quality and geometric fidelity over state-of-the-art baselines, reducing LPIPS by up to 28% while producing temporally coherent cloth dynamics.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。