HyperBones: Realtime Bone-driven Neural Garment Simulation with Hypernetwork Conditioning

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Srivastava, Astitva, Chen, Hsiao-Yu, Goldade, Ryan, Herholz, Philipp, Jiang, Zhongshi, Lin, Gene Wei-Chin, Yang, Lingchen, Sarafianos, Nikolaos, Stuyck, Tuur, Roble, Doug, Sharma, Avinash, Larionov, Egor
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866916060726296576
author Srivastava, Astitva
Chen, Hsiao-Yu
Goldade, Ryan
Herholz, Philipp
Jiang, Zhongshi
Lin, Gene Wei-Chin
Yang, Lingchen
Sarafianos, Nikolaos
Stuyck, Tuur
Roble, Doug
Sharma, Avinash
Larionov, Egor
author_facet Srivastava, Astitva
Chen, Hsiao-Yu
Goldade, Ryan
Herholz, Philipp
Jiang, Zhongshi
Lin, Gene Wei-Chin
Yang, Lingchen
Sarafianos, Nikolaos
Stuyck, Tuur
Roble, Doug
Sharma, Avinash
Larionov, Egor
contents Recent advances in garment simulation have brought high-quality results closer to real-time performance. Physics-based simulators can produce accurate motion, but remain too computationally expensive for interactive applications. In contrast, linear blend skinning is efficient, but cannot capture the complex dynamics of loose-fitting garments, often leading to unrealistic motion and visual artifacts. Neural methods offer a promising alternative, yet they still struggle to animate loose clothing plausibly under strict runtime constraints. We present a fast and physically plausible approach for dynamic garment simulation. Our method trains a reduced-space neural dynamics simulator composed of independent coarse- and fine-level components. At the coarse level, the garment is driven by a set of virtual bones integrated with a lightweight neural network. Fine-scale wrinkle details are then recovered using a trained convolutional neural map. By decoupling identity-specific computation from real-time neural integration, our architecture maintains high performance while supporting diverse body shapes and motions. We further introduce an effective physics-supervision scheme that enables accurate results without relying on an external simulator. Experiments show that our method produces physically plausible garment dynamics, generalizes across a range of motions and body shapes, and supports a fixed set of garments. Our simulator runs at 300+ FPS on a commodity GPU, making it suitable for real-time applications.
format Preprint
id arxiv_https___arxiv_org_abs_2605_20460
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle HyperBones: Realtime Bone-driven Neural Garment Simulation with Hypernetwork Conditioning
Srivastava, Astitva
Chen, Hsiao-Yu
Goldade, Ryan
Herholz, Philipp
Jiang, Zhongshi
Lin, Gene Wei-Chin
Yang, Lingchen
Sarafianos, Nikolaos
Stuyck, Tuur
Roble, Doug
Sharma, Avinash
Larionov, Egor
Graphics
Computer Vision and Pattern Recognition
Recent advances in garment simulation have brought high-quality results closer to real-time performance. Physics-based simulators can produce accurate motion, but remain too computationally expensive for interactive applications. In contrast, linear blend skinning is efficient, but cannot capture the complex dynamics of loose-fitting garments, often leading to unrealistic motion and visual artifacts. Neural methods offer a promising alternative, yet they still struggle to animate loose clothing plausibly under strict runtime constraints. We present a fast and physically plausible approach for dynamic garment simulation. Our method trains a reduced-space neural dynamics simulator composed of independent coarse- and fine-level components. At the coarse level, the garment is driven by a set of virtual bones integrated with a lightweight neural network. Fine-scale wrinkle details are then recovered using a trained convolutional neural map. By decoupling identity-specific computation from real-time neural integration, our architecture maintains high performance while supporting diverse body shapes and motions. We further introduce an effective physics-supervision scheme that enables accurate results without relying on an external simulator. Experiments show that our method produces physically plausible garment dynamics, generalizes across a range of motions and body shapes, and supports a fixed set of garments. Our simulator runs at 300+ FPS on a commodity GPU, making it suitable for real-time applications.
title HyperBones: Realtime Bone-driven Neural Garment Simulation with Hypernetwork Conditioning
topic Graphics
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2605.20460