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

arXiv: https://arxiv.org/abs/2605.20460 · HTML: https://mlsanity.com/paper/2605.20460/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 26 of its 52 references that are in the map.
- First posted on arXiv 19 May 2026.

## Builds on (most cited first, 26 of 26)

- [FiLM: Visual Reasoning with a General Conditioning Layer](https://mlsanity.com/paper/1709.07871/) (2017)
- [On the Continuity of Rotation Representations in Neural Networks](https://mlsanity.com/paper/1812.07035/) (2018)
- [Learning Mesh-Based Simulation with Graph Networks](https://mlsanity.com/paper/2010.03409/) (2020)
- [TailorNet: Predicting Clothing in 3D as a Function of Human Pose, Shape and Garment Style](https://mlsanity.com/paper/2003.04583/) (2020)
- [LiveCap: Real-time Human Performance Capture from Monocular Video](https://mlsanity.com/paper/1810.02648/) (2018)
- [SNUG: Self-Supervised Neural Dynamic Garments](https://mlsanity.com/paper/2204.02219/) (2022)
- [HOOD: Hierarchical Graphs for Generalized Modelling of Clothing Dynamics](https://mlsanity.com/paper/2212.07242/) (2022)
- [DrapeNet: Garment Generation and Self-Supervised Draping](https://mlsanity.com/paper/2211.11277/) (2022)
- [Predicting Loose-Fitting Garment Deformations Using Bone-Driven Motion Networks](https://mlsanity.com/paper/2205.01355/) (2022)
- [Neural Cloth Simulation](https://mlsanity.com/paper/2212.11220/) (2022)
- [Robust Dual Gaussian Splatting for Immersive Human-centric Volumetric Videos](https://mlsanity.com/paper/2409.08353/) (2024)
- [Simplicits: Mesh-Free, Geometry-Agnostic, Elastic Simulation](https://mlsanity.com/paper/2407.09497/) (2024)
- [Garment3DGen: 3D Garment Stylization and Texture Generation](https://mlsanity.com/paper/2403.18816/) (2024)
- [ContourCraft: Learning to Resolve Intersections in Neural Multi-Garment Simulations](https://mlsanity.com/paper/2405.09522/) (2024)
- [Relightable Full-Body Gaussian Codec Avatars](https://mlsanity.com/paper/2501.14726/) (2025)
- [WordRobe: Text-Guided Generation of Textured 3D Garments](https://mlsanity.com/paper/2403.17541/) (2024)
- [Quaffure: Real-Time Quasi-Static Neural Hair Simulation](https://mlsanity.com/paper/2412.10061/) (2024)
- [GAPS: Geometry-Aware, Physics-Based, Self-Supervised Neural Garment Draping](https://mlsanity.com/paper/2312.01490/) (2023)
- [Neural Garment Dynamics via Manifold-Aware Transformers](https://mlsanity.com/paper/2407.06101/) (2024)
- [DIMO: Diverse 3D Motion Generation for Arbitrary Objects](https://mlsanity.com/paper/2511.07409/) (2025)
- [PhysGraph: Physics-Based Integration Using Graph Neural Networks](https://mlsanity.com/paper/2301.11841/) (2023)
- [Self-supervised Learning of Latent Space Dynamics](https://mlsanity.com/paper/2507.07440/) (2025)
- [Neuralocks: Real-Time Dynamic Neural Hair Simulation](https://mlsanity.com/paper/2507.05191/) (2025)
- [SkinCells: Sparse Skinning using Voronoi Cells](https://mlsanity.com/paper/2506.14714/) (2025)
- [CTSN: Predicting Cloth Deformation for Skeleton-based Characters with a Two-stream Skinning Network](https://mlsanity.com/paper/2305.18808/) (2023)
- [Neural Garment Dynamic Super-Resolution](https://mlsanity.com/paper/2412.06285/) (2024)

## Abstract (arXiv)

Recent advances in cloth simulation have led to accurate garment physics, but the methods are computationally expensive for real-time applications. In contrast, Linear Blend Skinning (LBS) is efficient, but cannot capture the complex dynamics of loose-fitting garments, 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-informed framework for dynamic garment simulation, consisting of a reduced-space neural dynamics simulator with independent coarse and fine-level components. At the coarse level, the garment is driven by virtual bones integrated with a lightweight neural network for predicting corrections over LBS. Fine-scale wrinkle details are then recovered using a convolutional MLP defined in UV space. By decoupling identity-specific computation from shape conditioning via hypernetwork, our neural framework offers high performance, trained using an effective physics-based self-supervised training paradigm without relying on an offline simulator. Experiments show that our method produces physically plausible garment dynamics, generalizes across diverse motions and unseen body shapes, and delivers over 30x speedup compared to state-of-the-art autoregressive neural simulators, achieving interactive inference at ~1 ms per frame on a consumer GPU.