The Conditional Analogy GAN: Swapping Fashion Articles on People Images

Jetchev, Nikolay; Bergmann, Urs

doi:10.1109/iccvw.2017.269

Cited by 145 publications

(104 citation statements)

References 7 publications

(21 reference statements)

Supporting

Mentioning

103

Contrasting

Order By: Relevance

“…In addition, pants, without providing any product images of them, are also generated by our model. This indicates that our model implicitly learns the co-occurrence between different fash-Reference Image Ta r g e t Clothing PRGAN [32,51] CAGAN [21] CRN [6] Encoder-Decoder Non-parametric VITON (ours) Figure 6: Qualitative comparisons of different methods. Our method effectively renders the target clothing on to a person.…”

Section: Qualitative Resultsmentioning

confidence: 97%

“…Note that for fairness, we modify their encoder-decoder generator to have the same structure as ours, so that it can also generate 256 × 192 images. Other implementation details are the same as in [21].…”

Section: Gans With Person Representationmentioning

confidence: 99%

“…Method IS Human PRGAN [32,51] 2.688 ± 0.098 27.3% CAGAN [21] 2.981 ± 0.087 21.8% CRN [6] 2.449 ± 0.070 69.1% Encoder-Decoder 2.455 ± 0.110 58.4% Non-parametric 3.373 ± 0.142 46.4% VITON (Ours)…”

Section: Figurementioning

confidence: 99%

See 2 more Smart Citations

VITON: An Image-Based Virtual Try-on Network

Han

et al. 2018

2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition

456

514

View full text Add to dashboard Cite

We present an image-based VIirtual Try-On Network (VITON) without using 3D information in any form, which seamlessly transfers a desired clothing item onto the corresponding region of a person using a coarse-to-fine strategy. Conditioned upon a new clothing-agnostic yet descriptive person representation, our framework first generates a coarse synthesized image with the target clothing item overlaid on that same person in the same pose. We further enhance the initial blurry clothing area with a refinement network. The network is trained to learn how much detail to utilize from the target clothing item, and where to apply to the person in order to synthesize a photo-realistic image in which the target item deforms naturally with clear visual patterns. Experiments on our newly collected dataset demonstrate its promise in the image-based virtual try-on task over state-of-the-art generative models. 1

show abstract

Section: Qualitative Resultsmentioning

confidence: 97%

Section: Gans With Person Representationmentioning

confidence: 99%

See 1 more Smart Citation

VITON: An Image-Based Virtual Try-on Network

Han

et al. 2018

2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition

456

514

View full text Add to dashboard Cite

show abstract

“…GAN-based methods directly generate warped clothing onto people. However, GAN-based methods require paired images [ 13 ], which consist of the person wearing some target clothing and only the clothing by itself, or categorized apparel images [ 6 ]. The annotation cost of such datasets is high.…”

Section: Related Workmentioning

confidence: 99%

UVIRT—Unsupervised Virtual Try-on Using Disentangled Clothing and Person Features

Tsunashima

Arase²,

Lam³

et al. 2020

Sensors

View full text Add to dashboard Cite

Virtual Try-on is the ability to realistically superimpose clothing onto a target person. Due to its importance to the multi-billion dollar e-commerce industry, the problem has received significant attention in recent years. To date, most virtual try-on methods have been supervised approaches, namely using annotated data, such as clothes parsing semantic segmentation masks and paired images. These approaches incur a very high cost in annotation. Even existing weakly-supervised virtual try-on methods still use annotated data or pre-trained networks as auxiliary information and the costs of the annotation are still significantly high. Plus, the strategy using pre-trained networks is not appropriate in the practical scenarios due to latency. In this paper we propose Unsupervised VIRtual Try-on using disentangled representation (UVIRT). After UVIRT extracts a clothes and a person feature from a person image and a clothes image respectively, it exchanges a clothes and a person feature. Finally, UVIRT achieve virtual try-on. This is all achieved in an unsupervised manner so UVIRT has the advantage that it does not require any annotated data, pre-trained networks nor even category labels. In the experiments, we qualitatively and quantitatively compare between supervised methods and our UVIRT method on the MPV dataset (which has paired images) and on a Consumer-to-Consumer (C2C) marketplace dataset (which has unpaired images). As a result, UVIRT outperform the supervised method on the C2C marketplace dataset, and achieve comparable results on the MPV dataset, which has paired images in comparison with the conventional supervised method.

show abstract

“…Compared to graphics models, image-based generative models are more computationally efficient. Jetchev and Bergmann[13] proposed a conditional analogy GAN to swap fashion articles, without other…”

mentioning

confidence: 99%

Toward Characteristic-Preserving Image-Based Virtual Try-On Network

Wang

Zheng

Liang

et al. 2018

Lecture Notes in Computer Science

293

433

View full text Add to dashboard Cite

Image-based virtual try-on systems for fitting a new in-shop clothes into a person image have attracted increasing research attention, yet is still challenging. A desirable pipeline should not only transform the target clothes into the most fitting shape seamlessly but also preserve well the clothes identity in the generated image, that is, the key characteristics (e.g. texture, logo, embroidery) that depict the original clothes. However, previous image-conditioned generation works fail to meet these critical requirements towards the plausible virtual try-on performance since they fail to handle large spatial misalignment between the input image and target clothes. Prior work explicitly tackled spatial deformation using shape context matching, but failed to preserve clothing details due to its coarse-to-fine strategy. In this work, we propose a new fully-learnable Characteristic-Preserving Virtual Try-On Network (CP-VTON) for addressing all real-world challenges in this task. First, CP-VTON learns a thin-plate spline transformation for transforming the in-shop clothes into fitting the body shape of the target person via a new Geometric Matching Module (GMM) rather than computing correspondences of interest points as prior works did. Second, to alleviate boundary artifacts of warped clothes and make the results more realistic, we employ a Try-On Module that learns a composition mask to integrate the warped clothes and the rendered image to ensure smoothness. Extensive experiments on a fashion dataset demonstrate our CP-VTON achieves the state-ofthe-art virtual try-on performance both qualitatively and quantitatively. Code is available at https://github.com/sergeywong/cp-vton.

show abstract

The Conditional Analogy GAN: Swapping Fashion Articles on People Images

Cited by 145 publications

References 7 publications

VITON: An Image-Based Virtual Try-on Network

VITON: An Image-Based Virtual Try-on Network

UVIRT—Unsupervised Virtual Try-on Using Disentangled Clothing and Person Features

Toward Characteristic-Preserving Image-Based Virtual Try-On Network

Contact Info

Product

Resources

About