Filters








1,960 Hits in 4.3 sec

Hierarchy Composition GAN for High-fidelity Image Synthesis [article]

Fangneng Zhan, Jiaxing Huang, Shijian Lu
2021 arXiv   pre-print
We design an innovative hierarchical composition mechanism that is capable of learning realistic composition geometry and handling occlusions while multiple foreground objects are involved in image composition  ...  This paper presents an innovative Hierarchical Composition GAN (HIC-GAN) that incorporates image synthesis in geometry and appearance domains into an end-to-end trainable network and achieves superior  ...  The Proposed Method This section presents our proposed AC-GAN for realistic image synthesis.  ... 
arXiv:1905.04693v3 fatcat:vnhhegxnlzfonp3pwhn754h3dm

Spatial Fusion GAN for Image Synthesis [article]

Fangneng Zhan, Hongyuan Zhu, Shijian Lu
2019 arXiv   pre-print
Recent advances in generative adversarial networks (GANs) have shown great potentials in realistic image synthesis whereas most existing works address synthesis realism in either appearance space or geometry  ...  The SF-GAN has been evaluated in two tasks: (1) realistic scene text image synthesis for training better recognition models; (2) glass and hat wearing for realistic matching glasses and hats with real  ...  Most existing GANs work towards synthesis realism in the appearance space.  ... 
arXiv:1812.05840v3 fatcat:uzent4sy35cpjkslziikyppuni

Spatial Fusion GAN for Image Synthesis

Fangneng Zhan, Hongyuan Zhu, Shijian Lu
2019 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)  
Recent advances in generative adversarial networks (GANs) have shown great potentials in realistic image synthesis whereas most existing works address synthesis realism in either appearance space or geometry  ...  The SF-GAN has been evaluated in two tasks: (1) realistic scene text image synthesis for training better recognition models; (2) glass and hat wearing for realistic matching glasses and hats with real  ...  Most existing GANs work towards synthesis realism in the appearance space.  ... 
doi:10.1109/cvpr.2019.00377 dblp:conf/cvpr/ZhanZL19 fatcat:mxijttgvlvfbfmuztb4nva2fpu

Towards Realistic 3D Embedding via View Alignment [article]

Fangneng Zhan, Shijian Lu, Changgong Zhang, Feiying Ma, Xuansong Xie
2020 arXiv   pre-print
Extensive experiments over two synthesis tasks (car synthesis with KITTI and pedestrian synthesis with Cityscapes) show that VA-GAN achieves high-fidelity composition qualitatively and quantitatively as  ...  This paper presents an innovative View Alignment GAN (VA-GAN) that composes new images by embedding 3D models into 2D background images realistically and automatically.  ...  Three typical approaches have been explored for image synthesis by using GANs, namely, direct image generation [1, 20] , image-to-image translation [13, 29] and image composition [16, 27] .  ... 
arXiv:2007.07066v1 fatcat:4ud4d6jpbrafzos3ob4tkwy7je

Towards Realistic Face Photo-Sketch Synthesis via Composition-Aided GANs [article]

Jun Yu, Xingxin Xu, Fei Gao, Shengjie Shi, Meng Wang, Dacheng Tao, and Qingming Huang
2020 arXiv   pre-print
Specially, we propose a novel composition-aided generative adversarial network (CA-GAN) for face photo-sketch synthesis.  ...  To tackle this challenge, in this work, we propose to use the facial composition information to help the synthesis of face sketch/photo.  ...  : Table I shows that using compositional loss decreases FID by 0.8 (40.5 → 39.7) for sketch synthesis, while both the image and the compositional masks are used as input.  ... 
arXiv:1712.00899v4 fatcat:nkyodfbo4veipp44ihea74jrc4

SketchyGAN: Towards Diverse and Realistic Sketch to Image Synthesis

Wengling Chen, James Hays
2018 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition  
Synthesizing realistic images from human drawn sketches is a challenging problem in computer graphics and vision.  ...  Compared to state-of-the-art image translation methods, our approach generates more realistic images and achieves significantly higher Inception Scores.  ...  Sketchbased image synthesis enables non-artists to create realistic images without significant artistic skill or domain expertise in image synthesis.  ... 
doi:10.1109/cvpr.2018.00981 dblp:conf/cvpr/ChenH18 fatcat:lzxxydseondylgvdohyaarkcei

SketchyGAN: Towards Diverse and Realistic Sketch to Image Synthesis [article]

Wengling Chen, James Hays
2018 arXiv   pre-print
Synthesizing realistic images from human drawn sketches is a challenging problem in computer graphics and vision.  ...  Compared to state-of-the-art image translation methods, our approach generates more realistic images and achieves significantly higher Inception Scores.  ...  Sketchbased image synthesis enables non-artists to create realistic images without significant artistic skill or domain expertise in image synthesis.  ... 
arXiv:1801.02753v2 fatcat:ah6wsvbtp5af7f35ubknnodffm

A Survey on Adversarial Image Synthesis [article]

William Roy, Glen Kelly, Robert Leer, Frederick Ricardo
2021 arXiv   pre-print
as possible future research directions in image synthesis with GAN.  ...  Among the many applications of GAN, image synthesis is the most well-studied one, and research in this area has already demonstrated the great potential of using GAN in image synthesis.  ...  The most common applications in image synthesis are primarily realistic-looking image synthesis, image manipulation, filling in missing pixels and art creations.  ... 
arXiv:2106.16056v2 fatcat:mivx26q4x5ampfi566tipcwv3e

DocSynth: A Layout Guided Approach for Controllable Document Image Synthesis [article]

Sanket Biswas, Pau Riba, Josep Lladós, Umapada Pal
2021 arXiv   pre-print
Despite significant progress on current state-of-the-art image generation models, synthesis of document images containing multiple and complex object layouts is a challenging task.  ...  The results highlight that our model can successfully generate realistic and diverse document images with multiple objects.  ...  Since this work introduces the first fundamental approach towards the problem of layout-guided document image synthesis, we try to conduct some ablation studies that are important for proposing our model  ... 
arXiv:2107.02638v1 fatcat:tokazsxarngwjkt5tcj3bc4ev4

Towards Photo-Realistic Virtual Try-On by Adaptively GeneratingPreserving Image Content [article]

Han Yang, Ruimao Zhang, Xiaobao Guo, Wei Liu, Wangmeng Zuo, Ping Luo
2020 arXiv   pre-print
However, it remains a big challenge to generate photo-realistic try-on images when large occlusions and human poses are presented in the reference person.  ...  In comparison to the state-of-the-art methods, ACGPN can generate photo-realistic images with much better perceptual quality and richer fine-details.  ...  The extensive applications of GAN further demonstrate its superiority in image synthesis. Fashion Analysis and Synthesis.  ... 
arXiv:2003.05863v1 fatcat:l24wmq6rkfghrjejsxgxomui4q

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
generate photo-realistic images that adhere to the input content.  ...  networks (GANs), variational autoencoders (VAEs), and flow-based methods have enabled more powerful and versatile image generation tasks.  ...  [3] proposed a non-parametric matching and hierarchical composition strategy to synthesize realistic images from semantic maps.  ... 
arXiv:2107.04240v2 fatcat:ticrsi27nzhozmw7dp7wwja2ni

Image Processing Using Multi-Code GAN Prior [article]

Jinjin Gu, Yujun Shen, Bolei Zhou
2020 arXiv   pre-print
Despite the success of Generative Adversarial Networks (GANs) in image synthesis, applying trained GAN models to real image processing remains challenging.  ...  In particular, we employ multiple latent codes to generate multiple feature maps at some intermediate layer of the generator, then compose them with adaptive channel importance to recover the input image  ...  Image Processing with GANs. GANs have been widely used for real image processing due to its great power of synthesizing photo-realistic images.  ... 
arXiv:1912.07116v2 fatcat:cxb6ezakbre6hhktd6hmctpk2u

Adversarial Open Domain Adaptation for Sketch-to-Photo Synthesis [article]

Xiaoyu Xiang, Ding Liu, Xiao Yang, Yiheng Zhu, Xiaohui Shen, Jan P. Allebach
2021 arXiv   pre-print
Compared with the recent competing methods, our approach shows impressive results in synthesizing realistic color, texture, and maintaining the geometric composition for various categories of open-domain  ...  In this paper, we explore open-domain sketch-to-photo translation, which aims to synthesize a realistic photo from a freehand sketch with its class label, even if the sketches of that class are missing  ...  Sketchygan: Towards diverse and realistic sketch to image synthesis.  ... 
arXiv:2104.05703v2 fatcat:m4kkb6kje5botkae4xe25pxdu4

Face sketch to photo translation using generative adversarial networks [article]

Nastaran Moradzadeh Farid, Maryam Saeedi Fard, Ahmad Nickabadi
2021 arXiv   pre-print
With the advent of adversarial generative models, an increasing number of methods have been proposed for sketch-to-image synthesis.  ...  images.  ...  Moreover, recently, [28] proposed Composition-Aided Generative Adversarial Network (CA-GAN).  ... 
arXiv:2110.12290v1 fatcat:4uddzximofdtfoyclxr4p3adpm

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  
system automatically generate photo-realistic images according to that input.  ...  networks (GANs), variational autoencoders (VAEs), and flow-based methods have enabled more powerful and versatile image generation approaches.  ...  [100] proposed a non-parametric matching and hierarchical composition strategy to synthesize realistic images from semantic maps.  ... 
doi:10.1007/s41095-021-0234-8 fatcat:ot6dyrrrsnakxob4jzw4zld7zu
« Previous Showing results 1 — 15 out of 1,960 results