Parametric design for human body modeling by wireframe-assisted deep learning

Huang, Jida; Kwok, Tsz-Ho; Zhou, Chi

doi:10.1016/j.cad.2018.10.004

Cited by 27 publications

(14 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…And the generated face model facilitates personalized design of the eyeglasses frame. In [16], a parametric design of human body modeling with deep neural network and linear regression method is proposed, which could be utilized for generative design, such as virtual try-on system.…”

Section: Garment Fitting Method Designing An Elegant 3dmentioning

confidence: 99%

Dual Adaptive Adjustment for Customized Garment Pattern

Zhu

Peng

Asl

2019

Scientific Programming

View full text Add to dashboard Cite

We present a dual adaptive garment slice adjustment technique for automatic resizing of apparel products with variant body shapes, and this technique can quickly generate clothed characters. Our first contribution is to propose a novel fit evaluation method. When a 2D garment pattern and a 3D draped garment have the same triangle topology connection, we calculate the shape variable of each triangle and output heat map simultaneously. For sewing a pattern to a newly targeted human body, we propose a fully automatic adjustment method that conforms to the body structure and is composed of two stages. In the coarse auto adjustment (CAA) stage, we propose a method of controlling the size of a garment by the length of a bounding box in five parts of the human body. Then, the garment pattern is automatically adjusted using the measured dimension, by stretching or shrinking. In the fine auto adjustment (FAA) stage, boundary vertices control the shape in the adjustment process. For better matching with the body, the vertices of the garment pattern boundary are relocated with the calculated moving distance and moving direction. As demonstrated in the results, our method enables fully automatic adjustment, preserving the original pattern style of garments between characters with vastly body shapes. Compared with the state-of-art 2D editing method, our proposed approach leads to time saving, and it achieves realistic garment effect compared to auto fitting methods.

show abstract

Section: Garment Fitting Method Designing An Elegant 3dmentioning

confidence: 99%

Dual Adaptive Adjustment for Customized Garment Pattern

Zhu

Peng

Asl

2019

Scientific Programming

View full text Add to dashboard Cite

show abstract

“…SCAPE model from mask images by designing a doublebranch DenseNet architecture. Recently, Huang et al [34] employ a fully connected network to regress the PCA space of the feature curves that decompose a 3D human mesh into various patches from semantic parameters. These feature curves keep the underlying spatial relations of various patches, and a full 3D human mesh can thus be generated by combining the patches.…”

Section: A Parametric Approachmentioning

confidence: 99%

Non-Parametric Anthropometric Graph Convolutional Network for Virtual Mannequin Reconstruction

Xie

Zhong

et al. 2020

IEEE Access

View full text Add to dashboard Cite

In this paper, we present a novel non-parametric method for precisely reconstructing a three dimensional (3D) virtual mannequin from anthropometric measurements and mask image(s) based on Graph Convolution Network (GCN). The proposed method avoids heavy dependence on a particular parametric body model such as SMPL or SCPAE and can predict mesh vertices directly, which is significantly more comfortable using a GCN than a typical Convolutional Neural Network (CNN). To further improve the accuracy of the reconstruction and make the reconstruction more controllable, we incorporate the anthropometric measurements into the developed GCN. Our non-parametric reconstruction results distinctly outperform the previous graph convolution method, both visually and in terms of anthropometric accuracy. We also demonstrate that the proposed network possesses the capability to reconstruct a plausible 3D mannequin from a single-view mask. The proposed method can be effortless extended to a parametric method by appending a Multilayer Perception (MLP) to regress the parametric space of the Principal Component Analysis (PCA) model to achieve 3D reconstruction as well. Extensive experimental results demonstrate that our anthropometric GCN itself is very useful in improving the reconstruction accuracy, and the proposed method is effective and robust for 3D mannequin reconstruction. INDEX TERMS Graph convolution network, non-parametric mannequin reconstruction, anthropometric mannequin design, parametric reconstruction.

show abstract

“…2 Furthermore, the post-processing is very cumbersome and tedious. Recently, Huang et al 30 propose a novel fully connected network to generate the 3D human model from semantic parameters. Their network predicts different mesh patches to form a complete human shape.…”

Section: Related Workmentioning

confidence: 99%

Structure-consistent customized virtual mannequin reconstruction from 3D scans based on optimization

Xie

Zhong

2019

Textile Research Journal

View full text Add to dashboard Cite

The 3D virtual mannequin has been widely used in apparel industry, and its importance is also increasing. This work develops a new 3D virtual mannequin reconstruction system based on optimization. All the mannequins reconstructed by the proposed approach share the identical topology, that is, there is a point-to-point correspondence among the mannequins, which will significantly facilitate much subsequent processing in fashion design, made-to-measure, and virtual try-on. The inputs to the proposed system contain a template human body, a raw scan (represented in mesh), and a very sparse corresponding landmarks set. The proposed approach substantially utilizes the optimization technology to drive the template to deform into a real scan. There is no special requirement on the raw meshes. The raw meshes may have a different number of vertices and triangles or may even be incomplete. The proposed method only needs 21 landmarks as hard-constraints to reconstruct a mannequin with tens of thousands of vertices. These landmarks can be extracted automatically for standard mannequin reconstruction. Besides the standard mannequin, the proposed system can also be used to reconstruct display mannequins, that is, mannequins with various poses. The experiments visualize the optimization procedure and verify that the optimization is efficient and effective. Quantitative analysis also proves that the reconstruction error satisfies the requirements of fashion design and tailoring.

show abstract

Parametric design for human body modeling by wireframe-assisted deep learning

Cited by 27 publications

References 28 publications

Dual Adaptive Adjustment for Customized Garment Pattern

Dual Adaptive Adjustment for Customized Garment Pattern

Non-Parametric Anthropometric Graph Convolutional Network for Virtual Mannequin Reconstruction

Structure-consistent customized virtual mannequin reconstruction from 3D scans based on optimization

Contact Info

Product

Resources

About