CLOTH-HUGS: Cloth Aware Human Gaussian Splatting
This work addresses the problem of realistic clothed human reconstruction for computer graphics and virtual reality, offering improved perceptual quality and geometric fidelity for loose garments and complex deformations.
Cloth-HUGS is a Gaussian Splatting framework for photorealistic clothed human reconstruction that explicitly disentangles body and clothing, achieving real-time rendering at over 60 FPS and reducing LPIPS by up to 28% over state-of-the-art baselines.
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.