CLOTH-HUGS: Cloth Aware Human Gaussian Splatting
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915942025396224 |
|---|---|
| author | Mubashshira, Sadia Amini, Nazanin Desai, Kevin |
| author_facet | Mubashshira, Sadia Amini, Nazanin Desai, Kevin |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_15875 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | CLOTH-HUGS: Cloth Aware Human Gaussian Splatting Mubashshira, Sadia Amini, Nazanin Desai, Kevin Computer Vision and Pattern Recognition 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. |
| title | CLOTH-HUGS: Cloth Aware Human Gaussian Splatting |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2604.15875 |