CLOTH-HUGS: Cloth Aware Human Gaussian Splatting

TL;DR

Cloth-HUGS is a neural rendering framework that separately models body and clothing for photorealistic human reconstruction, achieving high realism and real-time performance.

Contribution

It introduces a novel Gaussian-based representation with physics-inspired constraints and a multi-pass rendering strategy for improved cloth realism and efficiency.

Findings

Reduces LPIPS by up to 28% over baselines.

Achieves real-time rendering at over 60 FPS.

Improves perceptual quality and geometric fidelity.

Abstract

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.