3D Virtual Garment Modeling from RGB Images

Xu, Yi; Yang, Shanglin; Sun, Wei; Tan, Li Kuo; Li, Kefeng; Zhou, Hui

doi:10.1109/ismar.2019.00-28

Cited by 20 publications

(12 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Xu et al . [XYS*19] propose a multi‐task learning network that can identify the garment landmarks and segment the garment semantically at the same time. A pre‐defined garment template mesh is then deformed according to predicted landmarks to re‐construct the 3D garment model.…”

Section: Related Workmentioning

confidence: 99%

“…In order to find a simple yet effective way to model 3D garments, a variety of research has been carried out over the last decade. Some image‐based methods re‐construct 3D virtual garments from single‐view images [ZCF*13, JHK15, DDÖ*17, YPA*18] or a few images [XYS*19] from different views. Many existing work of this category employ certain garment templates and recover the garments in the input images by deforming the pre‐defined garment templates [CZL*15, DDÖ*17, YPA*18, XYS*19, SWY*22].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Garment Model Extraction from Clothed Mannequin Scan

Gao

Taketomi

2023

Computer Graphics Forum

View full text Add to dashboard Cite

Modelling garments with rich details require enormous time and expertise of artists. Recent works re‐construct garments through segmentation of clothed human scan. However, existing methods rely on certain human body templates and do not perform as well on loose garments such as skirts. This paper presents a two‐stage pipeline for extracting high‐fidelity garments from static scan data of clothed mannequins. Our key contribution is a novel method for tracking both tight and loose boundaries between garments and mannequin skin. Our algorithm enables the modelling of off‐the‐shelf clothing with fine details. It is independent of human template models and requires only minimal mannequin priors. The effectiveness of our method is validated through quantitative and qualitative comparison with the baseline method. The results demonstrate that our method can accurately extract both tight and loose garments within reasonable time.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Garment Model Extraction from Clothed Mannequin Scan

Gao

Taketomi

2023

Computer Graphics Forum

View full text Add to dashboard Cite

show abstract

“…The important ingredient of the 3D model-based virtual try-on system is to capture and reconstruct both the customers' body shapes and the garment geometry to replace the original garment with a new one. The garment modeling and capturing can be achieved by a RGB camera [46], an additional depth camera [6], and a high-resolution 4D scanner [31]. On the other hand, to estimate the body shapes, many previous works perform body parts segmentation [11,12,33] first, and then fit parametric body shape models (e.g., SMPL [26] or SCAPE [3]) to the person in the input photo [46,50] or a sequence of 3D point clouds [49].…”

Section: Virtual Try-onmentioning

confidence: 99%

“…The garment modeling and capturing can be achieved by a RGB camera [46], an additional depth camera [6], and a high-resolution 4D scanner [31]. On the other hand, to estimate the body shapes, many previous works perform body parts segmentation [11,12,33] first, and then fit parametric body shape models (e.g., SMPL [26] or SCAPE [3]) to the person in the input photo [46,50] or a sequence of 3D point clouds [49]. The captured data can be used to generate different garment detailed deformations [22,27] and to map garment images directly onto a 3D human model [28].…”

Section: Virtual Try-onmentioning

confidence: 99%

Per Garment Capture and Synthesis for Real-time Virtual Try-on

Chong¹,

Shen²,

Umetani³

et al. 2021

Preprint

View full text Add to dashboard Cite

Fig. 1. Our real-time system allows the user to virtually try-on various garments using different interactions, such as stretching the body and pulling the garment. With the proposed per garment and synthesis workflow, the detailed wrinkles are captured and synthesized according to different motions.Virtual try-on is a promising application of computer graphics and human computer interaction that can have a profound real-world impact especially during this pandemic. Existing image-based works try to synthesize a try-on image from a single image of a target garment, but it inherently limits the ability to react to possible interactions. It is difficult to reproduce the change of wrinkles caused by pose and body size change, as well as pulling and stretching of the garment by hand. In this paper, we propose an alternative per garment capture and synthesis workflow to handle such rich interactions by training the model with many systematically captured images. Our workflow is composed of two parts: garment capturing and clothed person image synthesis. We designed an actuated mannequin and an efficient capturing process that collects the detailed deformations of the target garments under diverse body sizes and poses. Furthermore, we proposed to use a custom-designed measurement garment, and we captured paired images of the measurement garment and the target garments. We then learn a mapping between the measurement garment and the target garments using deep image-to-image translation. The customer can then try on the target garments interactively during online shopping. The proposed workflow requires certain manual labor, but we believe that the cost is acceptable given that the retailers are already paying significant costs for hiring professional photographers and models, stylists, and editors to take photographs for promotion. Our method can remove the need of hiring these costly professionals. We evaluated the effectiveness of the proposed system with ablation studies and quality comparison with previous virtual try-on methods. We perform a user study to show our promising virtual try-on

show abstract

“…E STIMATING a personalized body shape is very important for virtual try-on and body measurement, which enables personalized avatar generation in VR/AR [1], [2], [3], [4]. Although it is straightforward to capture the personalized body shape when the person is naked or nearly naked, most people cannot accept this form of collection.…”

Section: Introductionmentioning

confidence: 99%

Learning to Infer Inner-Body Under Clothing From Monocular Video

Huang

Zhang

et al. 2023

IEEE Trans. Visual. Comput. Graphics

View full text Add to dashboard Cite

Accurately estimating the human inner-body under clothing is very important for body measurement, virtual try-on and VR/AR applications. In this paper, we propose the first method to allow everyone to easily reconstruct their own 3D inner-body under daily clothing from a self-captured video with the mean reconstruction error of 0.73cm within 15s. This avoids privacy concerns arising from nudity or minimal clothing. Specifically, we propose a novel two-stage framework with a Semantic-guided Undressing Network (SUNet) and an Intra-Inter Transformer Network (IITNet). SUNet learns semantically related body features to alleviate the complexity and uncertainty of directly estimating 3D inner-bodies under clothing. IITNet reconstructs the 3D inner-body model by making full use of intra-frame and inter-frame information, which addresses the misalignment of inconsistent poses in different frames. Experimental results on both public datasets and our collected dataset demonstrate the effectiveness of the proposed method. The code and dataset is available for research purposes at http://cic.tju.edu.cn/faculty/likun/projects/Inner-Body.

show abstract

3D Virtual Garment Modeling from RGB Images

Cited by 20 publications

References 47 publications

Garment Model Extraction from Clothed Mannequin Scan

Garment Model Extraction from Clothed Mannequin Scan

Per Garment Capture and Synthesis for Real-time Virtual Try-on

Learning to Infer Inner-Body Under Clothing From Monocular Video

Contact Info

Product

Resources

About