Coarse-to-Fine Clothing Image Generation with Progressively Constructed Conditional GAN

Kwon, Youngki; Kim, Soomin; Yoo, Donggeun; Yoon, Sung‐Eui

doi:10.5220/0007306900830090

Cited by 3 publications

(3 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Frid-Adar M [3] et al used GANs to synthesize medical images for data augmentation and improved the classification performance of medical problems with limited data. Applying the rough-to-detail approach to the conditional image generation model, Kwon Y [4] et al proposed a rough-to-detail conditional GAN (rtdGAN) for the problem of generating clothing images that separates the challenging single-stage image generation process into a reasonably simple multi-stage image generation process.Li D [5] et al used GAN to perform multivariate anomaly detection on time series data generated from CPSs and proposed a new MAD-GAN framework to train LSTM-RNNs on multivariate time series data. Mirzaei M S [6] et al proposed an end-to-end spatio-temporal conditional GAN based on the generator of LSTM and the discriminator of graph convolutional nets, which can generate plausible, realistic, semantically relevant and user-expected human motion animation sequences based on the input animation cues.…”

Section: Application Of Data Amplificationmentioning

confidence: 99%

TransCGan-based human motion generator

2023

Fifth International Conference on Computer Information Science and Artificial Intelligence (CISAI 2022)

View full text Add to dashboard Cite

The synthesis of human movement is used in a wide range of applications, such as in military, gaming, sports, medical, robotics and many other fields. The current common approach is based on the acquisition of human motion data by motion capture devices. However, employing this method to gather information on human movements is expensive, time-consuming, and subject to space constraints. In order to avoid these problems, our goal is to create a system that can generate a variety of naturalistic movements quickly and inexpensively. We assume that the creation of human motion is a complicated, non-linear process that is amenable to modeling with deep neural networks. First, using optical motion capture equipment, we collect a range of human motion data, which we then pre-process and annotate. After that-we combine Transformer with Conditional GAN (Cgan) to train this human motion generation model with the collected data. Finally, we evaluate this model by qualitative and qualitative means, which can generate multiple human motions from a high-dimensional potential space based on specified labels.

show abstract

Section: Application Of Data Amplificationmentioning

confidence: 99%

TransCGan-based human motion generator

2023

Fifth International Conference on Computer Information Science and Artificial Intelligence (CISAI 2022)

View full text Add to dashboard Cite

show abstract

“…In the literature of fashion image translation, Yoo et al [41] trained a network that converted an image of a dressed person's clothing to a fashion product image using multiple discriminators. For the same task, Kwon et al [16] introduced a coarse-to-fine scheme to reduce the visual artifacts produced by a GAN. These conventional methods were trained using a dataset of images collected from online fashion shopping malls.…”

Section: Introductionmentioning

confidence: 99%

Anime-to-real clothing: Cosplay costume generation via image-to-image translation

Koya

Katsurai

Maki³

et al. 2022

Multimed Tools Appl

View full text Add to dashboard Cite

Cosplay has grown from its origins at fan conventions into a billion-dollar global dress phenomenon. To facilitate the imagination and reinterpretation of animated images as real garments, this paper presents an automatic costume-image generation method based on image-to-image translation. Cosplay items can be significantly diverse in their styles and shapes, and conventional methods cannot be directly applied to the wide variety of clothing images that are the focus of this study. To solve this problem, our method starts by collecting and preprocessing web images to prepare a cleaned, paired dataset of the anime and real domains. Then, we present a novel architecture for generative adversarial networks (GANs) to facilitate high-quality cosplay image generation. Our GAN consists of several effective techniques to bridge the two domains and improve both the global and local consistency of generated images. Experiments demonstrated that, with quantitative evaluation metrics, the proposed GAN performs better and produces more realistic images than conventional methods. Our codes and pretrained model are available on the web.

show abstract

“…In the literature of fashion image translation, Yoo et al [39] trained a network that converted an image of a dressed person's clothing to a fashion product image by using multiple discriminators. For the same task, Kwon et al [16] introduced a coarse-to-fine scheme to reduce the visual artifacts produced by a GAN. These conventional methods were trained using a dataset of images collected from online fashion shopping malls.…”

Section: Introductionmentioning

confidence: 99%

Anime-to-Real Clothing: Cosplay Costume Generation via Image-to-Image Translation

Koya¹,

Katsurai²,

Maki³

et al. 2020

Preprint

View full text Add to dashboard Cite

Cosplay has grown from its origins at fan conventions into a billion-dollar global dress phenomenon. To facilitate imagination and reinterpretation from animated images to real garments, this paper presents an automatic costume image generation method based on image-to-image translation. Cosplay items can be significantly diverse in their styles and shapes, and conventional methods cannot be directly applied to the wide variation in clothing images that are the focus of this study. To solve this problem, our method starts by collecting and preprocessing web images to prepare a cleaned, paired dataset of the anime and real domains. Then, we present a novel architecture for generative adversarial networks (GANs) to facilitate highquality cosplay image generation. Our GAN consists of several effective techniques to fill the gap between the two domains and improve both the global and local consistency of generated images. Experiments demonstrated that, with two types of evaluation metrics, the proposed GAN achieves better performance than existing methods. We also showed that the images generated by the proposed method are more realistic than those generated by the conventional methods. Our codes and pretrained model are available on the web.

show abstract

Coarse-to-Fine Clothing Image Generation with Progressively Constructed Conditional GAN

Cited by 3 publications

References 20 publications

TransCGan-based human motion generator

TransCGan-based human motion generator

Anime-to-real clothing: Cosplay costume generation via image-to-image translation

Anime-to-Real Clothing: Cosplay Costume Generation via Image-to-Image Translation

Contact Info

Product

Resources

About