Filters








254 Hits in 3.0 sec

Face Destylization [article]

Fatemeh Shiri, Xin Yu, Fatih Porikli, Piotr Koniusz
2018 arXiv   pre-print
Numerous style transfer methods which produce artistic styles of portraits have been proposed to date.  ...  Furthermore, we illustrate our network can recover faces from stylized portraits and real paintings for which the stylized data was unavailable during the training phase.  ...  Several methods based on feed-forward neural networks [2] - [9] accelerate the style transfer for specific styles.  ... 
arXiv:1802.01237v1 fatcat:vsoaxxtwx5eqvo6ls4wmcspdsm

Automatic Semantic Style Transfer using Deep Convolutional Neural Networks and Soft Masks [article]

Huihuang Zhao, Paul L. Rosin, Yu-Kun Lai
2017 arXiv   pre-print
When standard neural style transfer approaches are used, the textures and colours in different semantic regions of the style image are often applied inappropriately to the content image, ignoring its semantic  ...  Both the soft masks and source images are provided as multichannel input to an augmented deep CNN framework for style transfer which incorporates a generative Markov random field (MRF) model.  ...  We also would like to thank NVIDIA for the GPU donation.  ... 
arXiv:1708.09641v1 fatcat:urf6hxpvqfcmdfylhtwevze5eu

From Reality to Perception: Genre-Based Neural Image Style Transfer

Zhuoqi Ma, Nannan Wang, Xinbo Gao, Jie Li
2018 Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence  
We introduce a novel thought for integrating artists' perceptions on the real world into neural image style transfer process.  ...  We hope that this work provides new insight for including artists' perceptions into neural style transfer process, and helps people to understand the underlying characters of the artist or the genre.  ...  This idea has been further developed to painting style transfer on head portraits [Selim et al., 2016] and style image synthesis [Li and Wand, 2016] .  ... 
doi:10.24963/ijcai.2018/485 dblp:conf/ijcai/MaWGL18 fatcat:iknfotjzqvgoleoslxltyn3u4q

Identity-Preserving Face Recovery from Stylized Portraits

Fatemeh Shiri, Xin Yu, Fatih Porikli, Richard Hartley, Piotr Koniusz
2019 International Journal of Computer Vision  
We develop an Identity-preserving Face Recovery from Portraits (IFRP) method that utilizes a Style Removal network (SRN) and a Discriminative Network (DN).  ...  Owing to the Spatial Transformer Network (STN), SRN automatically compensates for misalignments of stylized portraits to output aligned realistic face images.  ...  [8] decompose styles into perceptual factors and then manipulate them for the style transfer. Selim et al. [40] modify the content loss through a gain map for the transfer of paintings of head.  ... 
doi:10.1007/s11263-019-01169-1 fatcat:xsyg7t6worerphh3n2wryjemcm

Sensory Optimization: Neural Networks as a Model for Understanding and Creating Art [article]

Owain Evans
2019 arXiv   pre-print
It's possible to train convolutional neural networks (CNNs) to recognize objects without training them on any visual art.  ...  I argue that Deep Dream and Style Transfer show that CNNs can create a basic form of visual art, and that humans could create art by similar processes.  ...  Neural Style Transfer ("ST") is a technique that uses a recognition net to achieve a simplified version of properties 1 and 2.  ... 
arXiv:1911.07068v1 fatcat:fy2xtl2pzffednzgdaqk3yvmde

Automatic Portrait Segmentation for Image Stylization

Xiaoyong Shen, Aaron Hertzmann, Jiaya Jia, Sylvain Paris, Brian Price, Eli Shechtman, Ian Sachs
2016 Computer graphics forum (Print)  
Abstract Portraiture is a major art form in both photography and painting.  ...  In most instances, artists seek to make the subject stand out from its surrounding, for instance, by making it brighter or sharper.  ...  We also thank Flickr users "Olaf Trubel", "Woodleywonderworks", "RD Glamour Photography" and "Justin Law" for the pictures used in the paper.  ... 
doi:10.1111/cgf.12814 fatcat:xr2h3vovvff5hnaq6qldz5g45i

Stable and Controllable Neural Texture Synthesis and Style Transfer Using Histogram Losses [article]

Eric Risser, Pierre Wilmot, Connelly Barnes
2017 arXiv   pre-print
Recently, methods have been proposed that perform texture synthesis and style transfer by using convolutional neural networks (e.g. Gatys et al. [2015,2016]).  ...  This paper presents a multiscale synthesis pipeline based on convolutional neural networks that ameliorates these issues.  ...  Neural texture synthesis and style transfer. In this paper, for short, we use "neural" to refer to convolutional neural networks.  ... 
arXiv:1701.08893v2 fatcat:bpiwne2eqbd6tagai4s3f3ezpy

Using Artificial Intelligence Techniques to Emulate the Creativity of a Portrait Painter

Steve DiPaola, Graeme McCaig
2016 EVA London 2016 Electronic Visualisation and the Arts  
By incorporating more open ended creative, semantic and concept blending techniques, these new neural network based AI techniques allow us to better model the creative cognitive thinking process that human  ...  Traditional portrait artists use a specific but open human creativity, vision, technical and perception methodologies to create a painterly portrait of a live or photographed sitter.  ...  ACKNOWLEDGEMENTS We would like to thank Liane Gabora, Sara Salevati, Daniel McVeigh and Jon Waldie for their thoughts and contributions as well as NSERC and SSHRC funding agencies.  ... 
doi:10.14236/ewic/eva2016.32 dblp:conf/eva/DiPaolaM16 fatcat:z5o3u7ucj5aejj4fnr5wkpxkku

Identity-preserving Face Recovery from Portraits [article]

Fatemeh Shiri, Xin Yu, Fatih Porikli, Richard Hartley, Piotr Koniusz
2018 arXiv   pre-print
Our IFRP method consists of two components: Style Removal Network (SRN) and Discriminative Network (DN).  ...  In addition, our method can recover photorealistic faces from previously unseen stylized portraits, original paintings and human-drawn sketches.  ...  [35] modify the content loss through a gain map for the head portrait painting transfer. Wilmot et al. [45] use histogrambased losses in their objective and build on the Gatys et al.'  ... 
arXiv:1801.02279v2 fatcat:ufixln6lkfdj5a5xa6qzzxsrxq

Stylized Neural Painting [article]

Zhengxia Zou
2020 arXiv   pre-print
Our method can be also jointly optimized with neural style transfer that further transfers visual style from other images. Our code and animated results are available at .  ...  for rendering.  ...  In addition to the GAN based method, neural style transfer has also made breakthroughs in stylized image synthesis and is widely used for artwork creation [6, 13] .  ... 
arXiv:2011.08114v1 fatcat:5piqlshh2zfyzpxhjp2xiidgvy

Gated-GAN: Adversarial Gated Networks for Multi-Collection Style Transfer

Xinyuan Chen, Chang Xu, Xiaokang Yang, Li Song, Dacheng Tao
2018 IEEE Transactions on Image Processing  
An auxiliary classifier is used to recognize the style categories of transferred images, thereby helping the generative networks generate images in multiple styles.  ...  The discriminative networks are used to distinguish whether the input image is a stylized or genuine image.  ...  [27] extended this idea to head portrait painting transfer by imposing novel spatial constraints to avoid facial deformations. Luan et al.  ... 
doi:10.1109/tip.2018.2869695 pmid:30222565 fatcat:vjk5eufctrdpxle7be2d4ilzae

Compare the performance of the models in art classification

Wentao Zhao, Dalin Zhou, Xinguo Qiu, Wei Jiang, Khanh N.Q. Le
2021 PLoS ONE  
The models were compared based on their abilities for classifying genres, styles and artists.  ...  In this study, we tested 7 different models on 3 different datasets under the same experimental setup to compare their art classification performances when either using or not using transfer learning.  ...  [19] introduced a two-stage image classification approach including a deep convolutional neural network (DCNN) and a shallow neural network to improve the style classification accuracy.  ... 
doi:10.1371/journal.pone.0248414 pmid:33711046 fatcat:afryicfsajgmdgykmjjsv46p3u

Image Neural Style Transfer with Global and Local Optimization Fusion

Hui-Huang Zhao, Paul L. Rosin, Yu-Kun Lai, Mu-Gang Lin, Qin-Yun Liu
2019 IEEE Access  
INDEX TERMS Deep neural networks, style transfer, Markov random field, gram matrix, local patch.  ...  This paper presents a new image synthesis method for image style transfer.  ...  ACKNOWLEDGMENT The authors would like to thank NVIDIA for the GPU donation.  ... 
doi:10.1109/access.2019.2922554 fatcat:uskpk7vtyvez5pveppxbnqlgvq

STALP: Style Transfer with Auxiliary Limited Pairing [article]

David Futschik, Michal Kučera, Michal Lukáč, Zhaowen Wang, Eli Shechtman, Daniel Sýkora
2021 arXiv   pre-print
We demonstrate how to train an image translation network that can perform real-time semantically meaningful style transfer to a set of target images with similar content as the source image.  ...  We demonstrate its practical utility on various applications including video stylization, style transfer to panoramas, faces, and 3D models.  ...  We are also grateful to Zuzana Studená, Štěpánka Sýkorová, Jolana Sýkorová, Graciela Bombalova-Bogra, Adrian Morgan, and Muchalogy for providing style exemplars and input video sequences.  ... 
arXiv:2110.10501v1 fatcat:vlh62lwzwrelremlzjzmcrbsiy

Resolution enhancement in the recovery of underdrawings via style transfer by generative adversarial deep neural networks

2021 IS&T International Symposium on Electronic Imaging Science and Technology  
Fast track article for IS&T International Symposium on Electronic Imaging 2021: Computer Vision and Image Analysis of Art 2021 proceedings.  ...  The last author would like to thank the Getty Research Center for access to its Research Library, where some of the above research was conducted.  ...  As an additional benefit our work here will enable comparisons between prior work using computational deep neural networks and generative adversarial neural networks for the problem of style transfer in  ... 
doi:10.2352/issn.2470-1173.2021.14.cvaa-017 fatcat:w5c2tgk4ynhz3kv7opq4acj7ry
« Previous Showing results 1 — 15 out of 254 results