Filters








9 Hits in 3.5 sec

STGAN: A Unified Selective Transfer Network for Arbitrary Image Attribute Editing [article]

Ming Liu, Yukang Ding, Min Xia, Xiao Liu, Errui Ding, Wangmeng Zuo, Shilei Wen
2019 arXiv   pre-print
Furthermore, selective transfer units are incorporated with encoder-decoder to adaptively select and modify encoder feature for enhanced attribute editing.  ...  Arbitrary attribute editing generally can be tackled by incorporating encoder-decoder and generative adversarial networks.  ...  Conclusion In this paper, we study the problem of arbitrary image attribute editing for selective transfer perspective, and present a STGAN model by incorporating difference attribute vector and selective  ... 
arXiv:1904.09709v1 fatcat:7wtborudqncj7e4dnkznowg6ca

STGAN: A Unified Selective Transfer Network for Arbitrary Image Attribute Editing

Ming Liu, Yukang Ding, Min Xia, Xiao Liu, Errui Ding, Wangmeng Zuo, Shilei Wen
2019 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)  
Furthermore, selective transfer units are incorporated with encoder-decoder to adaptively select and modify encoder feature for enhanced attribute editing.  ...  Abstract Arbitrary attribute editing generally can be tackled by incorporating encoder-decoder and generative adversarial networks.  ...  Conclusion In this paper, we study the problem of arbitrary image attribute editing for selective transfer perspective, and present a STGAN model by incorporating difference attribute vector and selective  ... 
doi:10.1109/cvpr.2019.00379 dblp:conf/cvpr/0018DXLDZW19 fatcat:4krufkz26rhmnb2kfmdzrcxgg4

Lifespan Age Transformation Synthesis [article]

Roy Or-El, Soumyadip Sengupta, Ohad Fried, Eli Shechtman, Ira Kemelmacher-Shlizerman
2020 arXiv   pre-print
We propose a novel multi-domain image-to-image generative adversarial network architecture, whose learned latent space models a continuous bi-directional aging process.  ...  Our framework can predict a full head portrait for ages 0-70 from a single photo, modifying both texture and shape of the head.  ...  O.F. was supported by the Brown Institute for Media Innovation. All images in this manuscript are licensed under creative commons license and were taken from the FFHQ dataset.  ... 
arXiv:2003.09764v2 fatcat:r3nlbqutv5dnxdgxmtn7kycwfi

Covering up bias in CelebA-like datasets with Markov blankets: A post-hoc cure for attribute prior avoidance [article]

Vinay Uday Prabhu, Dian Ang Yap, Alexander Wang, John Whaley
2019 arXiv   pre-print
In this paper, we address this and propose a post-hoc solution that utilizes an Ising attribute prior learned in the attribute space and showcase its efficacy via qualitative experiments.  ...  Attribute prior avoidance entails subconscious or willful non-modeling of (meta)attributes that datasets are oft born with, such as the 40 semantic facial attributes associated with the CelebA and CelebA-HQ  ...  STGAN: A UNIFIED SELECTIVE TRANSFER NETWORK FOR ARBITRARY IMAGE ATTRIBUTE EDITING We also carry out experiments on STGAN, a model built by Liu et al. (Liu et al., 2019) extending He et al.'s work.  ... 
arXiv:1907.12917v1 fatcat:rqwh2at4hzfmrkuu4zkixvcwbi

Image-to-Image Translation: Methods and Applications [article]

Yingxue Pang, Jianxin Lin, Tao Qin, Zhibo Chen
2021 arXiv   pre-print
Image-to-image translation (I2I) aims to transfer images from a source domain to a target domain while preserving the content representations.  ...  segmentation, style transfer, restoration, and pose estimation.  ...  They propose RelGAN and STGAN, respectively, to satisfy arbitrary image attribute editing with relative attributes.  ... 
arXiv:2101.08629v2 fatcat:i6pywjwnvnhp3i7cmgza2slnle

A comprehensive survey on semantic facial attribute editing using generative adversarial networks [article]

Ahmad Nickabadi, Maryam Saeedi Fard, Nastaran Moradzadeh Farid, Najmeh Mohammadbagheri
2022 arXiv   pre-print
Semantic facial attribute editing is the process of varying the values of one or more attributes of a face image while the other attributes of the image are not affected.  ...  In this paper, we survey the recent works and advances in semantic facial attribute editing.  ...  STGAN provides selective transfer units (STUs), which replace well-known skip-connections in U-Net structures and are applied after each encoder layer.  ... 
arXiv:2205.10587v1 fatcat:thpe4crcgndifb5mhtuveww4ji

EvoGAN: An Evolutionary Computation Assisted GAN [article]

Feng Liu, HanYang Wang, Jiahao Zhang, Ziwang Fu, Aimin Zhou, Jiayin Qi, Zhibin Li
2021 arXiv   pre-print
Specifically, we use the Facial Action Coding System (FACS) as the encoding of an EA and use a pre-trained GAN to generate human facial images, and then use a pre-trained classifier to recognize the expression  ...  The image synthesis technique is relatively well established which can generate facial images that are indistinguishable even by human beings.  ...  We thank the anonymous reviewers and our study participants for their time and helpful feedback.  ... 
arXiv:2110.11583v1 fatcat:i7lwfzsowbecblcav6omjuckta

Unsupervised Eyeglasses Removal in the Wild [article]

Bingwen Hu, Zhedong Zheng, Ping Liu, Wankou Yang, Mingwu Ren
2020 arXiv   pre-print
To address the limitation, we propose a unified eyeglass removal model called Eyeglasses Removal Generative Adversarial Network (ERGAN), which could handle different types of glasses in the wild.  ...  The experiment shows that our method could serve as a pre-processing method for these tasks.  ...  [41] presents a unified selective transfer network for arbitrary image attribute editing (STGAN), by combining difference attribute vector and selective transfer unit (STUs) in autoencoder network.  ... 
arXiv:1909.06989v4 fatcat:meigab4njrf2jm54sujzodazzi

Conditional Generative Adversarial Networks for Domain Transfer: A Survey

Guoqiang Zhou, Yi Fan, Jiachen Shi, Yuyuan Lu, Jun Shen
2022 Applied Sciences  
Generative Adversarial Network (GAN), deemed as a powerful deep-learning-based silver bullet for intelligent data generation, has been widely used in multi-disciplines.  ...  Furthermore, conditional GAN (CGAN) introduces artificial control information on the basis of GAN, which is more practical for many specific fields, though it is mostly used in domain transfer.  ...  conversion of landscape photo [15] Attribute edition Object style editing [38] Object outline editing [33] Facial attribute editing [71] Image synthesis Converting the semantic mask to a photo  ... 
doi:10.3390/app12168350 fatcat:4qjfoetexfaevoptzecu5i2jqy