Filters








4,384 Hits in 4.4 sec

Semantically Consistent Hierarchical Text to Fashion Image Synthesis with an Enhanced-Attentional Generative Adversarial Network

Kenan Emir Ak, Joo Hwee Lim, Jo Yew Tham, Ashraf Kassim
2019 2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW)  
In this paper, we present the enhanced Attentional Generative Adversarial Network (e-AttnGAN) with improved training stability for text-to-image synthesis. e-AttnGAN's integrated attention module utilizes  ...  In addition to multimodal similarity learning for text and image features of AttnGAN [28], cosine and feature matching losses of real and generated images are included while employing a classification  ...  Attentional adversarial generative network (AttnGAN) uses attention over word embeddings within an input sequence to generate images guided by the deep attentional multimodal similarity model (DAMSM).  ... 
doi:10.1109/iccvw.2019.00379 dblp:conf/iccvw/AkLTK19 fatcat:cit4iochkzezrg6lyb6mgaky5i

TailorGAN: Making User-Defined Fashion Designs [article]

Lele Chen, Justin Tian, Guo Li, Cheng-Haw Wu, Erh-Kan King, Kuan-Ting Chen, Shao-Hang Hsieh, Chenliang Xu
2020 arXiv   pre-print
And, the model's capability is generalized to achieve single-attribute manipulation by adversarial learning.  ...  In this paper, we consider a task: given a reference garment image A and another image B with target attribute (collar/sleeve), generate a photo-realistic image which combines the texture from reference  ...  Related Work Generative Adversarial Network (GAN) [9] is one of the most popular deep generative models and has shown impressive results in image synthesis studies, like image editing [23, 29] and  ... 
arXiv:2001.06427v2 fatcat:z2yuf3eh3zg2zjeccivf2he54u

TailorGAN: Making User-Defined Fashion Designs

Lele Chen, Justin Tian, Guo Li, Cheng-Haw Wu, Erh-Kan King, Kuan-Ting Chen, Shao-Hang Hsieh, Chenliang Xu
2020 2020 IEEE Winter Conference on Applications of Computer Vision (WACV)  
And, the model's capability is generalized to achieve single-attribute manipulation by adversarial learning.  ...  In this paper, we consider a task: given a reference garment image A and another image B with target attribute (collar/sleeve), generate a photorealistic image which combines the texture from reference  ...  Related Work Generative Adversarial Network (GAN) [9] is one of the most popular deep generative models and has shown impressive results in image synthesis studies, like image editing [23, 29] and  ... 
doi:10.1109/wacv45572.2020.9093416 dblp:conf/wacv/ChenTLWKCHX20 fatcat:eaoes36h3vfirexpzyjdaztbve

A State-of-the-Art Review on Image Synthesis with Generative Adversarial Networks

Lei Wang, Wei Chen, Wenjia Yang, Fangming Bi, Fei Richard Yu
2020 IEEE Access  
INDEX TERMS Generative adversarial networks, image synthesis, image-to-image translation, image editing, cartoon generation.  ...  Generative Adversarial Networks (GANs) have achieved impressive results in various image synthesis tasks, and are becoming a hot topic in computer vision research because of the impressive performance  ...  [83] proposed an image editing approach called Fashion Editing Generative Adversarial Network (FE-GAN) by using a multi-scale attention normalization.  ... 
doi:10.1109/access.2020.2982224 fatcat:p5uxjh4cybfw5grp6ldhkpukrm

Language Guided Fashion Image Manipulation with Feature-wise Transformations [article]

Mehmet Günel, Erkut Erdem, Aykut Erdem
2018 arXiv   pre-print
Developing techniques for editing an outfit image through natural sentences and accordingly generating new outfits has promising applications for art, fashion and design.  ...  In this work, we propose FiLMedGAN, which leverages feature-wise linear modulation (FiLM) to relate and transform visual features with natural language representations without using extra spatial information  ...  Related Work Our model is based on Generative Adversarial Networks (GANs) [9] .  ... 
arXiv:1808.04000v1 fatcat:zy2yb5bvkvffjk3nznxbhsdp2u

Spatially Constrained GAN for Face and Fashion Synthesis [article]

Songyao Jiang, Hongfu Liu, Yue Wu, Yun Fu
2021 arXiv   pre-print
Image generation has raised tremendous attention in both academic and industrial areas, especially for the conditional and target-oriented image generation, such as criminal portrait and fashion design  ...  To enhance the spatial controllability, a generator network is specially designed to take a semantic segmentation, a latent vector and an attribute-level label as inputs step by step.  ...  , and finally use attribute labels to synthesize attribute-specific contents in the generated image.  ... 
arXiv:1905.02320v2 fatcat:lul47gjj65a4np76nifm5tloyi

Table of Contents

2021 IEEE transactions on multimedia  
Bouchara AttentionFGAN: Infrared and Visible Image Fusion Using Attention-Based Generative Adversarial Networks . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .  ...  Mei Deep Learning for Multimedia Processing Staged Sketch-to-Image Synthesis via Semi-supervised Generative Adversarial Networks . . . . . . . . . . . . . . . . . . . . . . . . . . . .Arbitrarily-Oriented  ... 
doi:10.1109/tmm.2021.3132246 fatcat:el7u2udtybddrpbl5gxkvfricy

Deep image synthesis from intuitive user input: A review and perspectives

Yuan Xue, Yuan-Chen Guo, Han Zhang, Tao Xu, Song-Hai Zhang, Xiaolei Huang
2021 Computational Visual Media  
networks (GANs), variational autoencoders (VAEs), and flow-based methods have enabled more powerful and versatile image generation approaches.  ...  system automatically generate photo-realistic images according to that input.  ...  Another interesting application of taking visual attributes as input is fashion design. Lee and Lee [131] proposed a GAN model with an attentional discriminator for attribute-to-fashion generation.  ... 
doi:10.1007/s41095-021-0234-8 fatcat:ot6dyrrrsnakxob4jzw4zld7zu

Deep Image Synthesis from Intuitive User Input: A Review and Perspectives [article]

Yuan Xue, Yuan-Chen Guo, Han Zhang, Tao Xu, Song-Hai Zhang, Xiaolei Huang
2021 arXiv   pre-print
networks (GANs), variational autoencoders (VAEs), and flow-based methods have enabled more powerful and versatile image generation tasks.  ...  generate photo-realistic images that adhere to the input content.  ...  Another interesting application of taking visual attributes as input is fashion design. Lee et al. [60] proposes a GAN model with an attentional discriminator for attribute-to-fashion generation.  ... 
arXiv:2107.04240v2 fatcat:ticrsi27nzhozmw7dp7wwja2ni

Image Modification using Text with GANs

Fenil Doshi, Parth Doshi, Jimit Gandhi, Khushmann Dwivedi, Dr. Ramchandra Mangrulkar
2020 International Journal of Computer Applications Technology and Research  
The authors aim to modify the relevant features of an image using a natural language description of the target image, such that the irrelevant features are not modified.  ...  The proposed architecture generates images at a high resolution to maintain the aesthetic quality of the image and ensures that the irrelevant content of the original image is not affected.  ...  The recent push in research in this domain can be attributed to the success of generative architectures such as Generative Adversarial Networks (GANs) and Variational Autoencoders (VAE).  ... 
doi:10.7753/ijcatr0911.1001 fatcat:ujisbfkwmjec5gpnn3l7qoirn4

Conditional Adversarial Generative Flow for Controllable Image Synthesis [article]

Rui Liu, Yu Liu, Xinyu Gong, Xiaogang Wang, Hongsheng Li
2019 arXiv   pre-print
Flow-based generative models show great potential in image synthesis due to its reversible pipeline and exact log-likelihood target, yet it suffers from weak ability for conditional image synthesis, especially  ...  In this paper, based on modeling a joint probabilistic density of an image and its conditions, we propose a novel flow-based generative model named conditional adversarial generative flow (CAGlow).  ...  Unpaired image-to-image translation using cycle- consistent adversarial networks. In ICCV, 2017. 2  ... 
arXiv:1904.01782v1 fatcat:cgnesvhuffctxfk3kecack6drq

Conditional Introspective Variational Autoencoder for Image Synthesis

Kun Zheng, Yafan Cheng, XiaoJun Kang, Hong Yao, Tian Tian
2020 IEEE Access  
Our model only consists of encoder (E), generator (G) and classifier (C), where E and G can be adversarially optimized, and C helps to boost conditional generation, improve authenticity and provide generation  ...  Experiments on MNIST and Fashion-MNIST data sets show that our model achieves real conditional synthesis performances with better diversity and fewer artifacts.  ...  This structure uses the convolutional network to extract the feature and improve the learning effect of generator network.  ... 
doi:10.1109/access.2020.3018228 fatcat:lr57e7dgq5bfhoktj77fvb3jee

PAINT: Photo-realistic Fashion Design Synthesis

Xiaoling Gu, Jie Huang, Yongkang Wong, Jun Yu, Jianping Fan, Pai Peng, Mohan S. Kankanhalli
2022 ACM Transactions on Multimedia Computing, Communications, and Applications (TOMCCAP)  
In the third stage, we leverage an Appearance Flow Network (AFN) to generate the fashion design images of other viewpoints from a single-view observation by learning 2D multi-scale appearance flow fields  ...  In the second stage, we propose a Texture Synthesis Network (TSN) to synthesize textures on all transformed semantic layouts.  ...  In particular, recent advances in image generative models encourage researchers to devote themselves to fashion image synthesis, such as AI-assisted fashion design [18, 23, 24, 32] , fashion image editing  ... 
doi:10.1145/3545610 fatcat:c26pgvlzwnet5mnovn4goobpoy

Fashion Meets Computer Vision: A Survey [article]

Wen-Huang Cheng, Sijie Song, Chieh-Yun Chen, Shintami Chusnul Hidayati, Jiaying Liu
2021 arXiv   pre-print
landmark detection, fashion parsing, and item retrieval, (2) Fashion analysis contains attribute recognition, style learning, and popularity prediction, (3) Fashion synthesis involves style transfer,  ...  Fashion is the way we present ourselves to the world and has become one of the world's largest industries.  ...  [102] later introduced a bi-level adversarial network architecture, where the first adversarial scheme was to reconstruct face images, and the second was to maintain face identity.  ... 
arXiv:2003.13988v2 fatcat:ajzvyn4ck5gqxk5ht5u3mrdmba

Using Photorealistic Face Synthesis and Domain Adaptation to Improve Facial Expression Analysis [article]

Behzad Bozorgtabar, Mohammad Saeed Rad, Hazim Kemal Ekenel and Jean-Philippe Thiran
2019 arXiv   pre-print
To this end, we propose a new attribute guided face image synthesis to perform a translation between multiple image domains using a single model.  ...  We evaluate the effectiveness of the proposed approach on several face datasets on generating realistic face images.  ...  In particular, Generative Adversarial Network (GAN) [7] variants have achieved state-of-the-art results for image-to-image translation task.  ... 
arXiv:1905.08090v1 fatcat:ehsfrdnq4bcmxk5fd25ilm5ysq
« Previous Showing results 1 — 15 out of 4,384 results