# SNUG: Self-Supervised Neural Dynamic Garments

arXiv: https://arxiv.org/abs/2204.02219 · HTML: https://mlsanity.com/paper/2204.02219/

## Key facts

- Cited by 83 papers in the map (data through 14 Oct 2026).
- Builds on 35 of its 65 references that are in the map.
- First posted on arXiv 5 Apr 2022.

## Builds on (most cited first, 30 of 35)

- [AMASS: Archive of Motion Capture as Surface Shapes](https://mlsanity.com/paper/1904.03278/) (2019)
- [PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitization](https://mlsanity.com/paper/1905.05172/) (2019)
- [Physics-Constrained Deep Learning for High-dimensional Surrogate Modeling and Uncertainty Quantification without Labeled Data](https://mlsanity.com/paper/1901.06314/) (2019)
- [DiffTaichi: Differentiable Programming for Physical Simulation](https://mlsanity.com/paper/1910.00935/) (2019)
- [ARCH: Animatable Reconstruction of Clothed Humans](https://mlsanity.com/paper/2004.04572/) (2020)
- [Multi-Garment Net: Learning to Dress 3D People from Images](https://mlsanity.com/paper/1908.06903/) (2019)
- [SCANimate: Weakly Supervised Learning of Skinned Clothed Avatar Networks](https://mlsanity.com/paper/2104.03313/) (2021)
- [Learning to Reconstruct People in Clothing from a Single RGB Camera](https://mlsanity.com/paper/1903.05885/) (2019)
- [SMPLicit: Topology-aware Generative Model for Clothed People](https://mlsanity.com/paper/2103.06871/) (2021)
- [NASA: Neural Articulated Shape Approximation](https://mlsanity.com/paper/1912.03207/) (2019)
- [Accelerating Eulerian Fluid Simulation With Convolutional Networks](https://mlsanity.com/paper/1607.03597/) (2016)
- [Self-supervised Single-view 3D Reconstruction via Semantic Consistency](https://mlsanity.com/paper/2003.06473/) (2020)
- [CLOTH3D: Clothed 3D Humans](https://mlsanity.com/paper/1912.02792/) (2019)
- [Detailed Human Avatars from Monocular Video](https://mlsanity.com/paper/1808.01338/) (2018)
- [LEAP: Learning Articulated Occupancy of People](https://mlsanity.com/paper/2104.06849/) (2021)
- [Deep Fashion3D: A Dataset and Benchmark for 3D Garment Reconstruction from Single Images](https://mlsanity.com/paper/2003.12753/) (2020)
- [imGHUM: Implicit Generative Models of 3D Human Shape and Articulated Pose](https://mlsanity.com/paper/2108.10842/) (2021)
- [Neural-GIF: Neural Generalized Implicit Functions for Animating People in Clothing](https://mlsanity.com/paper/2108.08807/) (2021)
- [DeepWrinkles: Accurate and Realistic Clothing Modeling](https://mlsanity.com/paper/1808.03417/) (2018)
- [The Power of Points for Modeling Humans in Clothing](https://mlsanity.com/paper/2109.01137/) (2021)
- [Detailed, accurate, human shape estimation from clothed 3D scan sequences](https://mlsanity.com/paper/1703.04454/) (2017)
- [Learning-Based Animation of Clothing for Virtual Try-On](https://mlsanity.com/paper/1903.07190/) (2019)
- [SIZER: A Dataset and Model for Parsing 3D Clothing and Learning Size Sensitive 3D Clothing](https://mlsanity.com/paper/2007.11610/) (2020)
- [MetaAvatar: Learning Animatable Clothed Human Models from Few Depth Images](https://mlsanity.com/paper/2106.11944/) (2021)
- [Label-Free Supervision of Neural Networks with Physics and Domain Knowledge](https://mlsanity.com/paper/1609.05566/) (2016)
- [GarNet: A Two-Stream Network for Fast and Accurate 3D Cloth Draping](https://mlsanity.com/paper/1811.10983/) (2018)
- [PBNS: Physically Based Neural Simulator for Unsupervised Garment Pose Space Deformation](https://mlsanity.com/paper/2012.11310/) (2020)
- [Learning a Shared Shape Space for Multimodal Garment Design](https://mlsanity.com/paper/1806.11335/) (2018)
- [Fully Convolutional Graph Neural Networks for Parametric Virtual Try-On](https://mlsanity.com/paper/2009.04592/) (2020)
- [DeePSD: Automatic Deep Skinning And Pose Space Deformation For 3D Garment Animation](https://mlsanity.com/paper/2009.02715/) (2020)

## Built on by (most cited first, 30 of 83)

- [BEDLAM: A Synthetic Dataset of Bodies Exhibiting Detailed Lifelike Animated Motion](https://mlsanity.com/paper/2306.16940/) (2023)
- [HOOD: Hierarchical Graphs for Generalized Modelling of Clothing Dynamics](https://mlsanity.com/paper/2212.07242/) (2022)
- [PhysAvatar: Learning the Physics of Dressed 3D Avatars from Visual Observations](https://mlsanity.com/paper/2404.04421/) (2024)
- [DrapeNet: Garment Generation and Self-Supervised Draping](https://mlsanity.com/paper/2211.11277/) (2022)
- [DiffAvatar: Simulation-Ready Garment Optimization with Differentiable Simulation](https://mlsanity.com/paper/2311.12194/) (2023)
- [Neural Cloth Simulation](https://mlsanity.com/paper/2212.11220/) (2022)
- [ISP: Multi-Layered Garment Draping with Implicit Sewing Patterns](https://mlsanity.com/paper/2305.14100/) (2023)
- [State of the Art in Dense Monocular Non-Rigid 3D Reconstruction](https://mlsanity.com/paper/2210.15664/) (2022)
- [Neural Point-based Shape Modeling of Humans in Challenging Clothing](https://mlsanity.com/paper/2209.06814/) (2022)
- [DIG: Draping Implicit Garment over the Human Body](https://mlsanity.com/paper/2209.10845/) (2022)
- [Garment3DGen: 3D Garment Stylization and Texture Generation](https://mlsanity.com/paper/2403.18816/) (2024)
- [Garment Recovery with Shape and Deformation Priors](https://mlsanity.com/paper/2311.10356/) (2023)
- [ContourCraft: Learning to Resolve Intersections in Neural Multi-Garment Simulations](https://mlsanity.com/paper/2405.09522/) (2024)
- [PERGAMO: Personalized 3D Garments from Monocular Video](https://mlsanity.com/paper/2210.15040/) (2022)
- [CloSET: Modeling Clothed Humans on Continuous Surface with Explicit Template Decomposition](https://mlsanity.com/paper/2304.03167/) (2023)
- [CaPhy: Capturing Physical Properties for Animatable Human Avatars](https://mlsanity.com/paper/2308.05925/) (2023)
- [Dress-1-to-3: Single Image to Simulation-Ready 3D Outfit with Diffusion Prior and Differentiable Physics](https://mlsanity.com/paper/2502.03449/) (2025)
- [Dressing Avatars: Deep Photorealistic Appearance for Physically Simulated Clothing](https://mlsanity.com/paper/2206.15470/) (2022)
- [Motion Guided Deep Dynamic 3D Garments](https://mlsanity.com/paper/2209.11449/) (2022)
- [Data-Free Learning of Reduced-Order Kinematics](https://mlsanity.com/paper/2305.03846/) (2023)
- [ReLoo: Reconstructing Humans Dressed in Loose Garments from Monocular Video in the Wild](https://mlsanity.com/paper/2409.15269/) (2024)
- [4DHumanOutfit: a multi-subject 4D dataset of human motion sequences in varying outfits exhibiting large displacements](https://mlsanity.com/paper/2306.07399/) (2023)
- [Single View Garment Reconstruction Using Diffusion Mapping Via Pattern Coordinates](https://mlsanity.com/paper/2504.08353/) (2025)
- [ToMiE: Towards Explicit Exoskeleton for the Reconstruction of Complicated 3D Human Avatars](https://mlsanity.com/paper/2410.08082/) (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)
- [ClotheDreamer: Text-Guided Garment Generation with 3D Gaussians](https://mlsanity.com/paper/2406.16815/) (2024)
- [SimAvatar: Simulation-Ready Avatars with Layered Hair and Clothing](https://mlsanity.com/paper/2412.09545/) (2024)
- [Physics-guided Shape-from-Template: Monocular Video Perception through Neural Surrogate Models](https://mlsanity.com/paper/2311.12796/) (2023)
- [PICA: Physics-Integrated Clothed Avatar](https://mlsanity.com/paper/2407.05324/) (2024)

## Abstract (arXiv)

We present a self-supervised method to learn dynamic 3D deformations of garments worn by parametric human bodies. State-of-the-art data-driven approaches to model 3D garment deformations are trained using supervised strategies that require large datasets, usually obtained by expensive physics-based simulation methods or professional multi-camera capture setups. In contrast, we propose a new training scheme that removes the need for ground-truth samples, enabling self-supervised training of dynamic 3D garment deformations. Our key contribution is to realize that physics-based deformation models, traditionally solved in a frame-by-frame basis by implicit integrators, can be recasted as an optimization problem. We leverage such optimization-based scheme to formulate a set of physics-based loss terms that can be used to train neural networks without precomputing ground-truth data. This allows us to learn models for interactive garments, including dynamic deformations and fine wrinkles, with two orders of magnitude speed up in training time compared to state-of-the-art supervised methods