CLOTH-HUGS: Cloth Aware Human Gaussian Splatting

• URL: http://arxiv.org/abs/2604.15875v1
• Date: Fri, 17 Apr 2026 09:22:58 GMT
• Title: CLOTH-HUGS: Cloth Aware Human Gaussian Splatting
• Abstract summary: We present Cloth-HUGS, a neural rendering framework for clothed human reconstruction that explicitly disentangles body and clothing.<n>Experiments show that Cloth-HUGS improves perceptual quality and geometric fidelity over state-of-the-art baselines.
• Score: 4.205692673448206
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• Learning High-Fidelity Cloth Animation via Skinning-Free Image Transfer [64.49436559408049]
  We present a novel method for generating 3D garment deformations from given body poses.<n>Our method significantly improves animation quality on various garment types and recovers finer wrinkles than state-of-the-art methods.
  arXiv  Detail & Related papers  (2025-12-05T10:28:08Z)
• PBDyG: Position Based Dynamic Gaussians for Motion-Aware Clothed Human Avatars [18.101742122988707]
  This paper introduces a novel clothed human model that can be learned from multiview RGB videos.<n>Our method realizes movement-dependent'' cloth deformation via physical simulation.<n>Experiments demonstrate that our method not only accurately reproduces appearance but also enables the reconstruction of avatars wearing highly deformable garments.
  arXiv  Detail & Related papers  (2024-12-05T18:53:06Z)
• DAGSM: Disentangled Avatar Generation with GS-enhanced Mesh [102.84518904896737]
  DAGSM is a novel pipeline that generates disentangled human bodies and garments from the given text prompts.<n>We first create the unclothed body, followed by a sequence of individual cloth generation based on the body.<n>Experiments have demonstrated that DAGSM generates high-quality disentangled avatars, supports clothing replacement and realistic animation, and outperforms the baselines in visual quality.
  arXiv  Detail & Related papers  (2024-11-20T07:00:48Z)
• DressRecon: Freeform 4D Human Reconstruction from Monocular Video [64.61230035671885]
  We present a method to reconstruct time-consistent human body models from monocular videos. We focus on extremely loose clothing or handheld object interactions. DressRecon yields higher-fidelity 3D reconstructions than prior art.
  arXiv  Detail & Related papers  (2024-09-30T17:59:15Z)
• Gaussian Garments: Reconstructing Simulation-Ready Clothing with Photorealistic Appearance from Multi-View Video [66.98046635045685]
  We introduce a novel approach for reconstructing realistic simulation-ready garment assets from multi-view videos. Our method represents garments with a combination of a 3D mesh and a Gaussian texture that encodes both the color and high-frequency surface details. This representation enables accurate registration of garment geometries to multi-view videos and helps disentangle albedo textures from lighting effects.
  arXiv  Detail & Related papers  (2024-09-12T16:26:47Z)
• PICA: Physics-Integrated Clothed Avatar [30.277983921620663]
  We introduce PICA, a novel representation for high-fidelity animatable clothed human avatars with physics-accurate dynamics, even for loose clothing. Our method achieves high-fidelity rendering of human bodies in complex and novel driving poses, significantly outperforming previous methods under the same settings.
  arXiv  Detail & Related papers  (2024-07-07T10:23:21Z)
• MOSS: Motion-based 3D Clothed Human Synthesis from Monocular Video [14.683309699648175]
  Single-view clothed human reconstruction holds a central position in virtual reality applications. Current methodologies often overlook the influence of motion on surface deformation, resulting in surfaces lacking the constraints imposed by global motion. We introduce Motion-Based 3D Clothed Humans Synthesis (MOSS), which employs kinematic information to achieve motion-aware Gaussian split on the human surface.
  arXiv  Detail & Related papers  (2024-05-21T13:57:53Z)
• AniDress: Animatable Loose-Dressed Avatar from Sparse Views Using Garment Rigging Model [58.035758145894846]
  We introduce AniDress, a novel method for generating animatable human avatars in loose clothes using very sparse multi-view videos. A pose-driven deformable neural radiance field conditioned on both body and garment motions is introduced, providing explicit control of both parts. Our method is able to render natural garment dynamics that deviate highly from the body and well to generalize to both unseen views and poses.
  arXiv  Detail & Related papers  (2024-01-27T08:48:18Z)
• DLCA-Recon: Dynamic Loose Clothing Avatar Reconstruction from Monocular Videos [15.449755248457457]
  We propose a method named DLCA-Recon to create human avatars from monocular videos. The distance from loose clothing to the underlying body rapidly changes in every frame when the human freely moves and acts. Our method can produce superior results for humans with loose clothing compared to the SOTA methods.
  arXiv  Detail & Related papers  (2023-12-19T12:19:20Z)
• VINECS: Video-based Neural Character Skinning [82.39776643541383]
  We propose a fully automated approach for creating a fully rigged character with pose-dependent skinning weights. We show that our approach outperforms state-of-the-art while not relying on dense 4D scans.
  arXiv  Detail & Related papers  (2023-07-03T08:35:53Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.