ClothCombo: Modeling Inter-Cloth Interaction for Draping Multi-Layered Clothes
Not on the map. Why?
Abstract (arXiv)
We present ClothCombo, a pipeline to drape arbitrary combinations of clothes on 3D human models with varying body shapes and poses. While existing learning-based approaches for draping clothes have shown promising results, multi-layered clothing remains challenging as it is non-trivial to model inter-cloth interaction. To this end, our method utilizes a GNN-based network to efficiently model the interaction between clothes in different layers, thus enabling multi-layered clothing. Specifically, we first create feature embedding for each cloth using a topology-agnostic network. Then, the draping network deforms all clothes to fit the target body shape and pose without considering inter-cloth interaction. Lastly, the untangling network predicts the per-vertex displacements in a way that resolves interpenetration between clothes. In experiments, the proposed model demonstrates strong performance in complex multi-layered scenarios. Being agnostic to cloth topology, our method can be readily used for layered virtual try-on of real clothes in diverse poses and combinations of clothes.
Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 34 of its 94 references that are in the map. First posted on arXiv 7 Apr 2023.
Builds on
34 of 94 references.
References · 34
- 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
- 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
- 2016Gaussian Error Linear Units (GELUs)cited by 3,431
- 2019Expressive Body Capture: 3D Hands, Face, and Body from a Single Imagecited by 1,600
- 2020Learning to Simulate Complex Physics with Graph Networkscited by 867
- 2018PointCNN: Convolution On X-Transformed Pointscited by 764
- 2020Discovering Symbolic Models from Deep Learning with Inductive Biasescited by 335
- 2019Multi-Garment Net: Learning to Dress 3D People from Imagescited by 244
- 2021SCANimate: Weakly Supervised Learning of Skinned Clothed Avatar Networkscited by 181
- 2021SMPLicit: Topology-aware Generative Model for Clothed Peoplecited by 154
- 2021Modulated Periodic Activations for Generalizable Local Functional Representationscited by 140
- 2020BCNet: Learning Body and Cloth Shape from A Single Imagecited by 118
22 more
- 2019CLOTH3D: Clothed 3D Humanscited by 114
- 2021Neural-GIF: Neural Generalized Implicit Functions for Animating People in Clothingcited by 102
- 2018DeepWrinkles: Accurate and Realistic Clothing Modelingcited by 90
- 2019Learning-Based Animation of Clothing for Virtual Try-Oncited by 89
- 2020SIZER: A Dataset and Model for Parsing 3D Clothing and Learning Size Sensitive 3D Clothingcited by 87
- 2022SNUG: Self-Supervised Neural Dynamic Garmentscited by 83
- 2018GarNet: A Two-Stream Network for Fast and Accurate 3D Cloth Drapingcited by 69
- 2018Learning a Shared Shape Space for Multimodal Garment Designcited by 52
- 2019Physics-as-Inverse-Graphics: Unsupervised Physical Parameter Estimation from Videocited by 43
- 2020DeePSD: Automatic Deep Skinning And Pose Space Deformation For 3D Garment Animationcited by 43
- 2022Predicting Loose-Fitting Garment Deformations Using Bone-Driven Motion Networkscited by 39
- 2022Neural Cloth Simulationcited by 36
- 2021Generating Datasets of 3D Garments with Sewing Patternscited by 34
- 2020MeshWalker: Deep Mesh Understanding by Random Walkscited by 32
- 2022DIG: Draping Implicit Garment over the Human Bodycited by 26
- 2020GarNet++: Improving Fast and Accurate Static3D Cloth Draping by Curvature Losscited by 24
- 2020Deep Detail Enhancement for Any Garmentcited by 22
- 2022Motion Guided Deep Dynamic 3D Garmentscited by 19
- 2022Spelunking the Deep: Guaranteed Queries on General Neural Implicit Surfaces via Range Analysiscited by 11
- 20193D Virtual Garment Modeling from RGB Imagescited by 10
- 2018Hierarchical Cloth Simulation using Deep Neural Networkscited by 5
- 2022Force-Aware Interface via Electromyography for Natural VR/AR Interactioncited by 5
Built on by
Citing papers per year: 2024: 5; 2025: 1; 2026: 1.
7 papers.
- 2024PhysAvatar: Learning the Physics of Dressed 3D Avatars from Visual Observationscited by 51
- 2024SENC: Handling Self-collision in Neural Cloth Simulationcited by 4
- 2024Dress-Me-Up: A Dataset & Method for Self-Supervised 3D Garment Retargetingcited by 1
- 2024A Comparative Study of Garment Draping Techniquescited by 1
- 2024Neural Garment Dynamic Super-Resolutioncited by 1
- 2025FNOPT: Resolution-Agnostic, Self-Supervised Cloth Simulation using Meta-Optimization with Fourier Neural Operatorscited by 0
- 2026Layering Virtual Try-Oncited by 0
- 2026Layering Virtual Try-On24 Jul 2026
- 2025FNOPT: Resolution-Agnostic, Self-Supervised Cloth Simulation using Meta-Optimization with Fourier Neural Operators5 Dec 2025
- 2024Neural Garment Dynamic Super-Resolution9 Dec 2024
- 2024SENC: Handling Self-collision in Neural Cloth Simulation17 Jul 2024
- 2024A Comparative Study of Garment Draping Techniques17 May 2024
- 2024PhysAvatar: Learning the Physics of Dressed 3D Avatars from Visual Observations5 Apr 2024
- 2024Dress-Me-Up: A Dataset & Method for Self-Supervised 3D Garment Retargeting6 Jan 2024