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

Heming Zhu ^{1,2,3 †} , Yu Cao^{1,2,4 †} , Hang Jin^{1,2 †}, Weikai Chen ⁵, Dong Du⁶, Zhangye Wang ³,
Shuguang Cui ^1,2, Xiaoguang Han^1,2,*

*Corresponding email: hanxiaoguang@cuhk.edu.cn
† Joint first authors

¹ The Chinese University of Hong Kong, Shenzhen   ² Shenzhen Research Institute of Big Data  
³ State Key Lab of CAD&CG, Zhejiang University   ⁴ Xidian University   ⁵ Tencent America  
⁶ University of Science and Technology of China  

Figure 1: We present Deep Fashion3D, a large-scale repository of 3D clothing models reconstructed from real garments. It contains over 2000 3D garment models, spanning 10 different cloth categories. Each model is richly labeld with groundtruth point cloud, multi-view real images, 3D body pose and a novel annotation named feature lines. With Deep Fashion3D, inferring the garment geometry from a single image becomes possible.

News

Overview

Download

• Dataset (Colored point cloud models are available!!!)
• Paper

Citation

1
2
3
4
5
6
7
8
9

@inproceedings{zhu2020deep,
    title={Deep Fashion3D: A Dataset and Benchmark for 3D Garment Reconstruction from Single Images}, 
    booktitle={Computer Vision -- ECCV 2020},
    author={Heming, Zhu and Yu, Cao and Hang, Jin and Weikai, Chen and Dong, Du and Zhangye, Wang and Shuguang, Cui and Xiaoguang, Han},
    year={2020},
    publisher={Springer International Publishing},
    pages={512--530},
    isbn={978-3-030-58452-8}
}

Dataset Discription

• Firstly, Deep Fashion3D contains 2078 models reconstructed from real garments, which covers 10 different categories and 563 garment instances. To the best of our knowledge, Deep Fashion3D covers much more garment categories than other publicly available datasets specialized for 3D garments.
• Secondly, Deep Fashion3D contains rich annotations including 3D feature lines, 3D body pose and the corresponded caliborated multi-view real images. It is worth to mention that Deep Fashion3D is the first dataset which presents feature line annotation tailored for 3D graments, which can provide strong priors for garment reasoning related tasks, e.g., 3D garment reconstruction, classification, retrieval, etc.
• Thirdly, each garment in Deep Fashion3D is randomly posed to enhance the variety of real clothing.

Dataset Statistics

Table 1 shows the statistics of each clothing categories of Deep Fashion3D. Deep Fashion3D contains 2078 models reconstructed from real garments, which covers 10 different categories.

Table 1: Statistics of the each clothing categories of Deep Fashion3D.

Data Examples

Figure 2: Example garment models of Deep Fashion3D.

Annotation Discription

Figure 3 demonstrated a quick skim through the annotations of Deep Fashion3D dataset. To facilitate future research on 3D garment reasoning and resconstruction task, we provide rich annotations along with the Deep Fashion3D dataset, which consists of the following components:

• Feature line annotation: A novel feature line annotation tailored for 3D gamrment is proposed in Deep Fashion3D dataset. Akin to facial landmarks, the feature lines denote the most prominent features of interest, e.g. the open boundaries, the neckline, cuff, waist, etc, that could provide strong priors for a faithful reconstruction of 3D garment.
• Calibrated multi-view real images: For each 3D clothing model, we provide corresponding caliborated multi-view real images, which are critical to generalizing the trained model to images in the wild.
• 3D pose: For each 3D clothing model, we label it which 3D pose represented by SMPL coefficients. Due to the highly coupled nature between human body and clothing, we believe the labeled 3D pose could be beneficial to infer the global shape and pose-dependent deformations of the garment model.

For more details about the dataset, please refer to dataset download page.

Figure 3: A quick skim through the annotations of Deep Fashion3D dataset.

Experimental Results

Benchmarking on Single-view Reconstruction

Figure 4: Experiment results against other methods.

Results on In-the-wild Images

Figure 5: Reconstruction from in-the-wild images using our approach.