2,685 Hits in 5.2 sec

Registering Explicit to Implicit: Towards High-Fidelity Garment mesh Reconstruction from Single Images [article]

Heming Zhu, Lingteng Qiu, Yuda Qiu, Xiaoguang Han
2022 arXiv   pre-print
To address this issue, we proposed a novel geometry inference framework ReEF that reconstructs topology-consistent layered garment mesh by registering the explicit garment template to the whole-body implicit  ...  Experiments demonstrate that our method notably outperforms its counterparts on single-image layered garment reconstruction and could bring high-quality digital assets for further content creation.  ...  To generate garments with different styles, Multi-Garment Net(MGN) [5] , BCNet [17] and SMPLicit [10] adopted either explicit parametric models or implicit parametric models trained on the digital  ... 
arXiv:2203.15007v1 fatcat:mgtg7e46dbdkll4jq565qc7jx4

Deep Fashion3D: A Dataset and Benchmark for 3D Garment Reconstruction from Single Images [article]

Heming Zhu, Yu Cao, Hang Jin, Weikai Chen, Dong Du, Zhangye Wang, Shuguang Cui, Xiaoguang Han
2020 arXiv   pre-print
Deep Fashion3D contains 2078 models reconstructed from real garments, which covers 10 different categories and 563 garment instances.  ...  To demonstrate the advantage of Deep Fashion3D, we propose a novel baseline approach for single-view garment reconstruction, which leverages the merits of both mesh and implicit representations.  ...  Unlike the general objects in ShapeNet [13] , the garment shape typically appears as a thin layer with open boundary.  ... 
arXiv:2003.12753v2 fatcat:75d7udwyzjh6rmhddafhtzdzfm

Implicit untangling

Thomas Buffet, Damien Rohmer, Loïc Barthe, Laurence Boissieux, Marie-Paule Cani
2019 ACM Transactions on Graphics  
animations of arbitrarily complex layered clothing.  ...  As our results show, our method can be used to generate plausible, new static shapes of garments when underwear has been added, as well as collision-free configurations enabling a user to safely launch  ...  CONCLUSION We described an implicit solution for untangling layered garments.  ... 
doi:10.1145/3306346.3323010 fatcat:ndglh6a66vcuxgh3ozynr5zrym

Learning Anchored Unsigned Distance Functions with Gradient Direction Alignment for Single-view Garment Reconstruction [article]

Fang Zhao, Wenhao Wang, Shengcai Liao, Ling Shao
2021 arXiv   pre-print
AnchorUDF represents 3D shapes by predicting unsigned distance fields (UDFs) to enable open garment surface modeling at arbitrary resolution.  ...  Extensive experiments on two public 3D garment datasets, i.e., MGN and Deep Fashion3D, demonstrate that AnchorUDF achieves the state-of-the-art performance on single-view garment reconstruction.  ...  BCNet [22] introduces a layered garment representation on top of the SMPL body model [26] and a generic skinning weights generating network to improve the expression ability of the garment model.  ... 
arXiv:2108.08478v2 fatcat:qegdzqgzdvabtn4zn72mid72c4

MulayCap: Multi-layer Human Performance Capture Using A Monocular Video Camera [article]

Zhaoqi Su and Weilin Wan and Tao Yu and Lingjie Liu and Lu Fang and Wenping Wang and Yebin Liu
2020 arXiv   pre-print
The method uses "multi-layer" representations for geometry reconstruction and texture rendering, respectively.  ...  The key technique behind is a Garment-from-Video (GfV) method for optimizing the garment shape and reconstructing the dynamic cloth to fit the input video sequence, based on a cloth simulation model which  ...  The use of the multi-layer representations enables more semantic modeling of human performance, in which the body, garment pieces, albedo, shading are separately modeled and elaborately integrated to produce  ... 
arXiv:2004.05815v3 fatcat:6k2hjcakzbd6ndsaqia44xkuye

The Power of Points for Modeling Humans in Clothing [article]

Qianli Ma and Jinlong Yang and Siyu Tang and Michael J. Black
2021 arXiv   pre-print
Point clouds have properties of both implicit and explicit representations that we exploit to model 3D garment geometry on a human body.  ...  Our model demonstrates superior quantitative and qualitative results in both multi-outfit modeling and unseen outfit animation. The code is available for research purposes.  ...  Our shape decoder is a coordinate-based multi-layer perceptron (MLP), reminiscent of the recent line of work on neural implicit surfaces [11, 44, 50] and neural radiance fields [46] .  ... 
arXiv:2109.01137v2 fatcat:c2grh7j3qbesdbt4susat3vecy

3D virtual apparel design for industrial applications

Marzia Fontana, Caterina Rizzi, Umberto Cugini
2005 Computer-Aided Design  
Our model is incorporated within a 3D graphical environment, and includes operators monitoring the whole design process of apparel, e.g. panel sewing, button/dart insertion, multi-layered fabric composition  ...  The integration of physics-based models within CAD systems for garment design leads to highly accurate cloth shape results for virtual prototyping and quality evaluation tasks.  ...  Di Piazza designer of the 2D patterns in Fig. 2 , and all colleagues that participated to the research projects on non-rigid materials modelling and simulation.  ... 
doi:10.1016/j.cad.2004.09.004 fatcat:vrjp7eaenzfivk2p7fjdrrdebq

TightCap: 3D Human Shape Capture with Clothing Tightness Field [article]

Xin Chen, Anqi Pang, Yang Wei, Lan Xui, Jingyi Yu
2021 arXiv   pre-print
To break the severe variations of the human poses and garments, we propose to model the clothing tightness - the displacements from the garments to the human shape implicitly in the global UV texturing  ...  Based on this 2D representation, we propose a novel framework to predicted clothing tightness via a novel tightness formulation, as well as an effective optimization scheme to further reconstruct multi-layer  ...  , so as to enable further multi-layer garment reconstruction.  ... 
arXiv:1904.02601v4 fatcat:qez4hn3g25afxn5kvrqejsivxe

BCNet: Learning Body and Cloth Shape from A Single Image [article]

Boyi Jiang, Juyong Zhang, Yang Hong, Jinhao Luo, Ligang Liu, Hujun Bao
2020 arXiv   pre-print
of our garment model.  ...  To this end, we propose a layered garment representation on top of SMPL and novelly make the skinning weight of garment independent of the body mesh, which significantly improves the expression ability  ...  A) Incorrect garment reconstruction due to unsupported garment type. B) Multi-layered garments are treated as a single layer garment.  ... 
arXiv:2004.00214v2 fatcat:e6i44tczsnfzbbivy6tolvlfy4

From Measured Fabric to the Simulation of Cloth

Nadia Magnenat-Thalmann, Christiane Luible, Pascal Volino, Etienne Lyard
2007 2007 10th IEEE International Conference on Computer-Aided Design and Computer Graphics  
In order to obtain high quality animations of dressed models, the properties of the simulated garment must first be evaluated in an accurate and adapted way.  ...  Various issues must be considered, and depending on the complexity of the simulated garments, tradeoffs must be made in order to reconcile the real features of the cloth (stitches, layers...) and the computational  ...  Multi-layered fabrics In order to give to a garment more stability in some areas for functional or aesthetical reasons, a second fabric layers can be added.  ... 
doi:10.1109/cadcg.2007.4407832 dblp:conf/cadgraphics/Magnenat-ThalmannLVL07 fatcat:zw22cg37jffkxh42j7wm3d6aiq

gDNA: Towards Generative Detailed Neural Avatars [article]

Xu Chen, Tianjian Jiang, Jie Song, Jinlong Yang, Michael J. Black, Andreas Geiger, Otmar Hilliges
2022 arXiv   pre-print
To capture the stochastic nature of high-frequency details in garments, we leverage an adversarial loss formulation that encourages the model to capture the underlying statistics.  ...  Specifically, we devise a multi-subject forward skinning module that is learned from only a few posed, un-rigged scans per subject.  ...  Pred-to-Scan metric does not apply to multi-layer surfaces from SMPLicit. Reposing Fitting Target Ours SMPLicit NPMs Figure 10 . Fitting and Reposing.  ... 
arXiv:2201.04123v2 fatcat:ciuinrl6onbfvc3aaihb7mgpxy

Machine learning for digital try-on: Challenges and progress

Junbang Liang, Ming C. Lin
2020 Computational Visual Media  
[18] is a multi-view, multi-stage framework to address ambiguity caused by camera projection (see Fig. 1 ). Their model performs several stages of error correction.  ...  body and garments, faithful modeling of garment material, and lossless transformation of garments between virtual and physical worlds.  ... 
doi:10.1007/s41095-020-0189-1 fatcat:abmjz2ogu5dztflwvjnp3vr57m

GarmentNets: Category-Level Pose Estimation for Garments via Canonical Space Shape Completion [article]

Cheng Chi, Shuran Song
2021 arXiv   pre-print
This paper tackles the task of category-level pose estimation for garments.  ...  This canonical space is defined across garments instances within a category, therefore, specifies the shared category-level pose.  ...  This concatenated feature is passed through an MLP (multi-layer perceptron) before aggregation.  ... 
arXiv:2104.05177v2 fatcat:62ntns5pkbbfpe2brrkog3dcre

PBNS: Physically Based Neural Simulator for Unsupervised Garment Pose Space Deformation [article]

Hugo Bertiche, Meysam Madadi, Sergio Escalera
2021 arXiv   pre-print
We present a methodology to automatically obtain Pose Space Deformation (PSD) basis for rigged garments through deep learning.  ...  Our solution is extremely efficient, handles multiple layers of cloth, allows unsupervised outfit resizing and can be easily applied to any custom 3D avatar.  ...  [31] explicitly apply a non-linear mapping with a Multi-Layer Perceptron (MLP) for a single fixed garment.  ... 
arXiv:2012.11310v3 fatcat:al6gzeekfza6rpnl37vwj5lzta

Research on the Application of Personalized Customized Virtual Design Method in Clothing

2017 DEStech Transactions on Computer Science and Engineering  
Based on the dynamic holographic product model of apparel products, the 3D virtual garment design method is applied in clothing personalized customization, and the clothing modeling based on physical-geometric  ...  Based on the dynamic holographic model of apparel 3D virtual design, real-time dynamic record of clothing modeling information in order to amend and improve.  ...  The process can be divided into three layers: the garment target design layer, the garment virtual manufacturing model construction layer and the Garment Application field simulation analysis layer. (1  ... 
doi:10.12783/dtcse/cii2017/17228 fatcat:wtslpzqhj5hh7ho37uvsppvudy
« Previous Showing results 1 — 15 out of 2,685 results