Realistic reconstruction of 3D clothing from an image has wide applications,
such as avatar creation and virtual try-on. This paper presents a novel
framework that reconstructs the texture map for 3D garments from a single image
with pose. Assuming that 3D garments are modeled by stitching 2D garment sewing
patterns, our specific goal is to generate a texture image for the sewing
patterns. A key component of our framework, the Texture Unwarper, infers the
original texture image from the input clothing image, which exhibits warping
and occlusion of texture due to the user's body shape and pose. The Texture
Unwarper effectively transforms between the input and output images by mapping
the latent spaces of the two images. By inferring the unwarped original texture
of the input garment, our method helps reconstruct 3D garment models that can
show high-quality texture images realistically deformed for new poses. We
validate the effectiveness of our approach through a comparison with other
methods and ablation studies. Additionally, we release a large dataset of
garment sewing patterns with textures and images of avatars wearing the
garments, which will be useful for future research on garment texture
reconstruction and synthesis.

该论文介绍了一种从图像中实现 3D 服装的逼真重建的方法，通过一种基于图像纹理的新框架，使用姿势信息从单张图像中生成 3D 服装的纹理图像，验证了该方法的有效性，并提供了一个大型数据集，对未来的服装纹理重建和合成研究具有重要参考价值。

DeepIron: 从单张图片预测无扭曲的服装纹理

DeepIron: Predicting Unwarped Garment Texture from a Single Image

While models of 3D clothing learned from real data exist, no method can
predict clothing deformation as a function of garment size. In this paper, we
introduce SizerNet to predict 3D clothing conditioned on human body shape and
garment size parameters, and ParserNet to infer garment meshes and shape under
clothing with personal details in a single pass from an input mesh. SizerNet
allows to estimate and visualize the dressing effect of a garment in various
sizes, and ParserNet allows to edit clothing of an input mesh directly,
removing the need for scan segmentation, which is a challenging problem in
itself. To learn these models, we introduce the SIZER dataset of clothing size
variation which includes $100$ different subjects wearing casual clothing items
in various sizes, totaling to approximately 2000 scans. This dataset includes
the scans, registrations to the SMPL model, scans segmented in clothing parts,
garment category and size labels. Our experiments show better parsing accuracy
and size prediction than baseline methods trained on SIZER. The code, model and
dataset will be released for research purposes.

本文介绍了 SizerNet 和 ParserNet 算法，前者可以预测基于人体形状和服装尺寸参数的三维服装的变形，后者可以直接编辑输入网格的服装，两者结合可以更准确地预测尺寸和形状，实验表明相比于基线方法，效果更好。

SIZER: 一个用于分析 3D 服装和学习尺寸敏感 3D 服装的数据集和模型

SIZER: A Dataset and Model for Parsing 3D Clothing and Learning Size  Sensitive 3D Clothing

This work presents CLOTH3D, the first big scale synthetic dataset of 3D
clothed human sequences. CLOTH3D contains a large variability on garment type,
topology, shape, size, tightness and fabric. Clothes are simulated on top of
thousands of different pose sequences and body shapes, generating realistic
cloth dynamics. We provide the dataset with a generative model for cloth
generation. We propose a Conditional Variational Auto-Encoder (CVAE) based on
graph convolutions (GCVAE) to learn garment latent spaces. This allows for
realistic generation of 3D garments on top of SMPL model for any pose and
shape.

CLOTH3D 是第一份大规模的 3D 服装人体序列的综合性合成数据集，并提供了基于条件变分自编码器和图卷积的生成模型，实现了在任何姿势和形状下逼真生成 3D 服装。