Filters








935 Hits in 5.9 sec

Controllable Person Image Synthesis with Attribute-Decomposed GAN [article]

Yifang Men, Yiming Mao, Yuning Jiang, Wei-Ying Ma, Zhouhui Lian
2020 arXiv   pre-print
This paper introduces the Attribute-Decomposed GAN, a novel generative model for controllable person image synthesis, which can produce realistic person images with desired human attributes (e.g., pose  ...  This strategy allows for the synthesis of more realistic output images and automatic separation of un-annotated attributes.  ...  To address the aforementioned challenges, we propose a novel controllable person image synthesis method via an Attribute-Decomposed GAN.  ... 
arXiv:2003.12267v4 fatcat:wz2itgztojaijak55gznxmqf4e

Controllable Person Image Synthesis With Attribute-Decomposed GAN

Yifang Men, Yiming Mao, Yuning Jiang, Wei-Ying Ma, Zhouhui Lian
2020 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)  
This paper introduces the Attribute-Decomposed GAN, a novel generative model for controllable person image synthesis, which can produce realistic person images with desired human attributes (e.g., pose  ...  This strategy allows for the synthesis of more realistic output images and automatic separation of un-annotated attributes.  ...  To address the aforementioned challenges, we propose a novel controllable person image synthesis method via an Attribute-Decomposed GAN.  ... 
doi:10.1109/cvpr42600.2020.00513 dblp:conf/cvpr/MenMJML20 fatcat:bm5uwozumbfhzgcbxxwfmgwyi4

Correspondence Learning for Controllable Person Image Generation [article]

Shilong Shen
2020 arXiv   pre-print
We present a generative model for controllable person image synthesis,as shown in Figure , which can be applied to pose-guided person image synthesis, i.e., converting the pose of a source person image  ...  Then, decomposed attribute encoder is used to extract the component features, which not only helps to establish a more accurate dense correspondence, but also realizes the clothing-guided person generation  ...  Method Description Our goal is to achieve controllable person image synthesis.  ... 
arXiv:2012.12440v1 fatcat:yzbzgnrgbzggtbd4iuntpqi2by

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  
Then, we discuss the challenges faced by GANs and introduce some methods to deal with these problems.  ...  In this paper, we introduce the recent research on GANs in the field of image processing, including image synthesis, image generation, image semantic editing, image-to-image translation, image super-resolution  ...  characters. 1) TEXT GUIDED PERSON IMAGE SYNTHESIS Zhou et al  ... 
doi:10.1109/access.2020.2982224 fatcat:p5uxjh4cybfw5grp6ldhkpukrm

Pose and Attribute Consistent Person Image Synthesis

Cheng Xu, Zejun Chen, Jiajie Mai, Xuemiao Xu, Shengfeng He
2022 ACM Transactions on Multimedia Computing, Communications, and Applications (TOMCCAP)  
In this paper, we explicitly address these two problems by proposing a Pose and Attribute Consistent Person Image Synthesis Network (PAC-GAN).  ...  Person Image Synthesis aims at transferring the appearance of the source person image into a target pose.  ...  The most related work to our PAC-GAN is AD-GAN [29] , which embeds the source image into style codes to achieve attribute-controllable person image synthesis.  ... 
doi:10.1145/3554739 fatcat:ygzaft666zhctgieqdsodz4ggu

LOHO: Latent Optimization of Hairstyles via Orthogonalization [article]

Rohit Saha and Brendan Duke and Florian Shkurti and Graham W. Taylor and Parham Aarabi
2021 arXiv   pre-print
Our approach decomposes hair into three attributes: perceptual structure, appearance, and style, and includes tailored losses to model each of these attributes independently.  ...  Using LOHO for latent space manipulation, users can synthesize novel photorealistic images by manipulating hair attributes either individually or jointly, transferring the desired attributes from reference  ...  MichiGAN [30] proposed a conditional synthesis GAN that allows controlled manipulation of hair.  ... 
arXiv:2103.03891v2 fatcat:hpghywrhwvhzjlyhcdvoowiboy

A Survey on Face Data Augmentation [article]

Xiang Wang and Kai Wang and Shiguo Lian
2019 arXiv   pre-print
In this paper, we systematically review the existing works of face data augmentation from the perspectives of the transformation types and methods, with the state-of-the-art approaches involved.  ...  However, collecting and labeling adequate samples with high quality and balanced distributions still remains a laborious and expensive work, and various data augmentation techniques have thus been widely  ...  (3) If controllable generation method is adopted, faces with specific features and attributes can be obtained.  ... 
arXiv:1904.11685v1 fatcat:phcwwc7gcfablgytt6itr6xade

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.  ...  This paper reviews recent works for image synthesis given intuitive user input, covering advances in input versatility, image generation methodology, benchmark datasets, and evaluation metrics.  ...  [130] introduced an attribute-decomposed GAN, where visual attributes, including clothes, are extracted from reference images and combined with target poses to generate target images with desired attributes  ... 
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.  ...  This paper reviews recent works for image synthesis given intuitive user input, covering advances in input versatility, image generation methodology, benchmark datasets, and evaluation metrics.  ...  [83] introduces Attribute-Decomposed GAN, where visual attributes including clothes are extracted from reference images and combined with target poses to generate target images with desired attributes  ... 
arXiv:2107.04240v2 fatcat:ticrsi27nzhozmw7dp7wwja2ni

StyleLight: HDR Panorama Generation for Lighting Estimation and Editing [article]

Guangcong Wang and Yinuo Yang and Chen Change Loy and Ziwei Liu
2022 arXiv   pre-print
During inference, given an LDR LFOV image, we propose a focal-masked GAN inversion method to find its latent code by the LDR panorama synthesis branch and then synthesize the HDR panorama by the HDR panorama  ...  synthesis branch.  ...  These image editing methods focus on controlling the latent code to control attributes of objects.  ... 
arXiv:2207.14811v1 fatcat:buf5pwhi5zcsvlyrn7h3yg3okm

Texture Deformation Based Generative Adversarial Networks for Face Editing [article]

WenTing Chen, Xinpeng Xie, Xi Jia, Linlin Shen
2018 arXiv   pre-print
Despite the significant success in image-to-image translation and latent representation based facial attribute editing and expression synthesis, the existing approaches still have limitations in the sharpness  ...  We also evaluate our approach qualitatively and quantitatively on facial attribute and facial expression synthesis.  ...  The proposed TDB-GAN can generate images with higher quality and more relative identity compared to the existing methods, due to the disentangled texture and deformation, and the identity loss.  ... 
arXiv:1812.09832v1 fatcat:nwwiu6pkcbeolmi23seok2kapa

CA-GAN: Weakly Supervised Color Aware GAN for Controllable Makeup Transfer [article]

Robin Kips, Pietro Gori, Matthieu Perrot, Isabelle Bloch
2020 arXiv   pre-print
This enables to learn a controllable synthesis of complex objects, and only requires a weak proxy of the image attribute that we desire to modify.  ...  We propose a new formulation for the makeup style transfer task, with the objective to learn a color controllable makeup style synthesis.  ...  Controllable Image Synthesis with GANs. In the field of GANs, efforts have recently been made to develop methods that can control one or more attributes of the generated images.  ... 
arXiv:2008.10298v1 fatcat:n4apgkkdlzbgreuemwx3zdosye

Semi-Latent GAN: Learning to generate and modify facial images from attributes [article]

Weidong Yin, Yanwei Fu, Leonid Sigal, Xiangyang Xue
2017 arXiv   pre-print
Generating and manipulating human facial images using high-level attributal controls are important and interesting problems.  ...  This paper proposes a novel model that learns how to both generate and modify the facial image from high-level semantic attributes.  ...  [28] studied the problem of automatic synthesis of realistic images from text using deep convolutional GANs. Yan et al.  ... 
arXiv:1704.02166v1 fatcat:tfw76sqzybcfnbokju5obx2jim

MorphGAN: One-Shot Face Synthesis GAN for Detecting Recognition Bias [article]

Nataniel Ruiz, Barry-John Theobald, Anurag Ranjan, Ahmed Hussein Abdelaziz, Nicholas Apostoloff
2020 arXiv   pre-print
Next, a conditional Generative Adversarial Network (GAN) conditioned on the original image and the rendered morphable model is used to produce the image of the original person with the new facial expression  ...  However, capturing a sufficiently large dataset with specific control over the attributes of interest is difficult.  ...  In this paper we use present a novel GAN-based face image generator with interpretable controls that allow precise manipulation of facial attributes.  ... 
arXiv:2012.05225v2 fatcat:w2w3xhj63vg6vmta56rkmbkb5e

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)  
To solve this challenging multi-modal image translation problem, we propose a novel Photo-reAlistic fashIon desigN synThesis (PAINT) framework, which decomposes the framework into three manageable stages  ...  Experimental results demonstrate that our method is capable of generating diverse photo-realistic multi-view fashion design images with fine-grained appearance details conditioned on the provided multiple  ...  Person Image Generation Pose guided person image generation aims to transfer person images from one pose to other poses, where the generated person is expected to be consistent with the conditioned pose  ... 
doi:10.1145/3545610 fatcat:c26pgvlzwnet5mnovn4goobpoy
« Previous Showing results 1 — 15 out of 935 results