Clothing simulation, particularly the modeling of clothing deformation on the human body, has been a significant research focus. State-of-the-art methods typically apply neural architectures in a rudimentary manner without adapting to garment deformation characteristics. This limitation necessitates additional processing to refine model outputs. To overcome these limitations, this paper introduces a transformer-based approach combined with graph neural networks to predict clothing deformations and generate images that accurately reflect human motion. Compared to existing methods, our approach captures finer details of clothing deformation while maintaining physical plausibility. Quantitative experiments demonstrate its superior performance across multiple evaluation metrics, while qualitative assessments show that our method outperforms current state-of-the-art techniques.
DuCYuFJiangM, et al.VTON-SCFA: a virtual try-on network based on the semantic constraints and flow alignment. IEEE Trans Multimed2023; 20: 777–791.
2.
NarainRArminSO’brienJ. Adaptive anisotropic remeshing for cloth simulation. ACM Trans Graph2012; 31(6): 1–10.
3.
BaraffDAndrewW. Large steps in cloth simulation. Seminal Graphics Papers: Pushing the Boundaries2023; 2: 767–778.
4.
LiuTSofienBKavanL. Quasi-newton methods for real-time simulation of hyperelastic materials. ACM Trans Graph2017; 36(3): 1–16.
5.
YuFZhangYLiH, et al.Phase contour enhancement network for clothing parsing. IEEE Trans Consum Electron2024; 70(1): 2784–2793.
6.
JiaXZhongXYeM, et al.Complementary data augmentation for cloth-changing person re-identification. IEEE Trans Image Process2022; 31: 4227–4239.
7.
BerticheHMadadiMTylsonE, et al.DeePSD: automatic deep skinning and pose space deformation for 3D garment animation. In: Proceedings of the IEEE/CVF international conference on computer vision, Montreal, QC, Canada, 10–17 October 2021, pp.5471–5480.
8.
BerticheHMadadiMEscaleraS. PBNS: physically based neural simulation for unsupervised garment pose space deformation. ACM Trans Graph2021; 40(6): 1–14.
9.
LoperMMahmoodNRomeroJ, et al.SMPL: a skinned multi-person linear model. ACM Trans Graph2015; 34(6): 1–16.
10.
MerrillDGrimshawA. High performance and scalable radix sorting: a case study of implementing dynamic parallelism for GPU computing. Parallel Process Lett2011; 21(2): 245–272.
11.
ProvotX.Collision and self-collision handling in cloth model dedicated to design garments. In: Computer animation and simulation’97: proceedings of the eurographics workshop in Budapest, 02-03 September1997, pp. 177–189.
12.
TangMTongRNarainR, et al.A GPU‐based streaming algorithm for high‐resolution cloth simulation. Comput Graph Forum2013; 32(7): 21–30.
13.
KavanLCollinsSŽáraJ, et al.Geometric skinning with approximate dual quaternion blending. ACM Trans Graph2008; 27(4): 1–23.
14.
VassilevTSpanlangBChrysanthouY. Fast cloth animation on walking avatars. Comput Graph Forum2001; 20(3): 260–267.
15.
PatelCLiaoZPons-MollTailornetG.: predicting clothing in 3d as a function of human pose, shape and garment style. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, online meeting, 14-19June2020, pp. 7363–7373.
16.
SantestebanIOtaduyACasasD. Learning‐based animation of clothing for virtual try‐on. Comput Graph Forum2019; 38(2): 355–366.
17.
SoltaniAHuangHWuJ, et al.Synthesizing 3d shapes via modeling multi-view depth maps and silhouettes with deep generative networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, Honolulu, HI, USA, 21-26 July 2017, pp. 2511–2519.
18.
GrigorevABlackMHilligesO. HOOD: hierarchical graphs for generalized modelling of clothing dynamics. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, Vancouver, BC, Canada, 17–24 June 2023, pp. 16965–16974.
19.
SantestebanIOtaduyMACasasDSNUG: self-supervised neural dynamic garments. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition.New Orleans, LA, USA, June 19-24; 2022: 8130–8140.
20.
YangZZhongXZhongZ, et al.Win-win by competition: auxiliary-free cloth-changing person re-identification. IEEE Trans Image Process2023; 32: 2985–2999.
21.
YuFHuaADuC, et al.VTON-MP: multi-pose virtual try-on via appearance flow and feature filtering. IEEE Trans Consum Electron2023; 69(4): 1101–1113.
22.
PeiLWangTKesdoganT, et al.Neural garment dynamics via manifold‐aware transformers. Comput Graph Forum. 2024; 43(2): e15028.
23.
LahnerZDanielCTonyDeepwrinklesT.: accurate and realistic clothing modeling. In: Proceedings of the European conference on computer vision,Munich, Germany, 08-14 September 2018.
24.
KocabasMAthanasiouNBlackVibeMJ.: video inference for human body pose and shape estimation. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, online meeting, 14-19June2020, pp. 5252–5262.
25.
HanXChangGYuY. DeepSketch2Face: a deep learning based sketching system for 3D face and caricature modeling. ACM Trans Graph2017; 36(4): 1–12.
26.
LyuWDongXWongR, et al.A multimodal transformer: fusing clinical notes with structured EHR data for interpretable in-hospital mortality prediction. AMIA Annu Symp Proc2022; 2022: 719–728.
27.
MohamedOLassnerCPons-MollGet al.Neural body fitting: unifying deep learning and model based human pose and shape estimation. In: IEEE international conference on 3D vision,Verona, Italy, 05-08September2018, pp. 484–494.
28.
YuFXiaoZLiuL, et al.BiaCanDet: bioelectrical impedance analysis for breast cancer detection with space-time attention neural network. Expert Syst Appl2025; 269: 126223.
29.
YangZLinMZhongX, et al.Good is bad: causality inspired cloth-debiasing for cloth-changing person re-identification. In: Proceedings of the IEEE/CVF international conference on computer vision, Vancouver, BC, Canada, 17–24 June 2023, pp. 1472–1481.
30.
AlldieckTPons-MollGTheobaltCet al.Tex2shape: detailed full human body geometry from a single image. In: Proceedings of the IEEE/CVF international conference on computer vision, Seoul, Korea, 27 October-02 November2019, pp. 2293–2303.
31.
BhatnagarBTiwariGTheobaltC, et al.Multi-garment net: learning to dress 3d people from images. In: Proceedings of the IEEE/CVF international conference on computer vision, Seoul, Korea (South), 27 October 2019–02 November 2019, pp. 5419–5429.
32.
ZhongXGuCYeM, et al.Graph complemented latent representation for few-shot image classification. IEEE Trans Multimed2023; 25: 1979–1990.
33.
YuFChenZJiangM, et al.Smart clothing system with multiple sensors based on digital twin technology. IEEE Internet Things J2023; 10(7): 6377–6387.
34.
GundogduEConstantinVSeifoddiniA, et al.Garnet: a two-stream network for fast and accurate 3d cloth draping. In: Proceedings of the IEEE/CVF international conference on computer vision, Seoul, Korea (South), 27 October 2019–02 November 2019, pp. 8738–8747.
35.
ZouXHanXWongW. Cloth4d: a dataset for clothed human reconstruction. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, Vancouver, BC, Canada, 17–24 June 2023, pp. 12847–12857.
36.
YuFYuCTianZ, et al.Intelligent wearable system with motion and emotion recognition based on digital twin technology. IEEE Internet Things J2024; 11(15): 26314–26328.
37.
YouHZhongXLiuW, et al.Converting artificial neural networks to ultra-low-latency spiking neural networks for action recognition. IEEE Trans Cogn Dev Syst2024; 16(4): 1533–1545.
38.
LyuWZhengSPangL, et al.Attention-enhancing backdoor attacks against BERT-based models. Findings of the association for computational linguistics: EMNLP. ACL, 2023, pp. 10672–10690.
39.
YuFYuCTianZ, et al.Multimodal wearable system with dual-frequency enhancement network for risk recognition. IEEE Internet Things J2025; 12(11): 17634–17648.
40.
BerticheHMadadiMEscaleraS. Cloth3d: clothed 3d humans. Proceedings of the European Conference on Computer Vision2020; 12365: 344–359.
