Filters








959 Hits in 6.9 sec

Design of Painting Art Style Rendering System Based on Convolutional Neural Network

Xingyu Xie, Bin Lv
2021 Scientific Programming  
Experiments were conducted on the painting art style rendering system based on the proposed model.  ...  Convolutional Neural Network- (CNN-) based GAN models mainly suffer from problems such as data set limitation and rendering efficiency in the segmentation and rendering of painting art.  ...  (a) Oil painting-based painting art style rendering. (b) Sketch painting-based painting art style rendering. (c) Ink wash painting-based painting art style rendering.  ... 
doi:10.1155/2021/4708758 doaj:869e936a8b08472d9aef0b6f40ba7e76 fatcat:qixnntb53nhmfeamqx4xafpcpy

Design and Application of Intelligent Processing Technology for Animation Images Based on Deep Learning

Jie Zheng, Hasan Ali Khattak
2022 Mobile Information Systems  
Image stylistic migration based on convolutional neural networks has developed as a central research path in recent years, and attempts on style migration have evolved as well.  ...  However, there are few studies on style migration. In this paper, we propose a deep learning-based solution to the problem of anime-style migration.  ...  Because of advancements in graphics processors, deep learning based on convolutional neural networks has witnessed a second spring in recent years.  ... 
doi:10.1155/2022/9438086 fatcat:inqttsk6cjh7ba3cqegv34pmye

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  
The target style representation is reconstructed based on the semantic correspondence between real world photo and painting, which enable the perception guidance in style transfer.  ...  We introduce a novel thought for integrating artists' perceptions on the real world into neural image style transfer process.  ...  IAGR 20170103), in part by the Leading Talent of Technological Innovation of Ten-Thousands Talents Program under Grant CS31117200001.  ... 
doi:10.24963/ijcai.2018/485 dblp:conf/ijcai/MaWGL18 fatcat:iknfotjzqvgoleoslxltyn3u4q

Progressive Full Data Convolutional Neural Networks for Line Extraction from Anime-Style Illustrations

Yuchen Xin, Hon-Cheng Wong, Sio-Long Lo, Junliang Li
2019 Applied Sciences  
In order to address these problems, in this paper, we propose progressive full data convolutional neural networks for extracting lines from anime-style illustrations.  ...  Extracting line drawings from finished illustrations is one of the main tasks in drawing a manuscript and also a crucial task in the common painting process.  ...  Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/app10010041 fatcat:vdi534nfengnbhenhkh7dmh4py

Deep Convolutional Nets Learning Classification for Artistic Style Transfer

R. Dinesh Kumar, E. Golden Julie, Y. Harold Robinson, S. Vimal, Gaurav Dhiman, Murugesh Veerasamy, Antonio J. Peña
2022 Scientific Programming  
Usually, there are methods to render an input image in the style of famous art works. This issue of generating art is normally called nonphotorealistic rendering.  ...  Here, the images are input where one is the content image which contains the features you want to retain in the output image and the style reference image which contains patterns or images of famous paintings  ...  Today, there are few existing systems which replicate art from famous painters. One of these methods is style transfer using a neural network [4] .  ... 
doi:10.1155/2022/2038740 fatcat:as5sycc6wfdjlhgkibhg3hneue

A Neural Algorithm of Artistic Style [article]

Leon A. Gatys, Alexander S. Ecker, Matthias Bethge
2015 arXiv   pre-print
Here we introduce an artificial system based on a Deep Neural Network that creates artistic images of high perceptual quality.  ...  In fine art, especially painting, humans have mastered the skill to create unique visual experiences through composing a complex interplay between the content and style of an image.  ...  The class of Deep Neural Networks that are most powerful in image processing tasks are called Convolutional Neural Networks.  ... 
arXiv:1508.06576v2 fatcat:ycwowlzlwncahdfvp6c2eufcq4

A Neural Algorithm of Artistic Style

Leon Gatys, Alexander Ecker, Matthias Bethge
2016 Journal of Vision  
Networks. 1, 2 Here we introduce an artificial system based on a Deep Neural Network that creates artistic images of high perceptual quality.  ...  In fine art, especially painting, humans have mastered the skill to create unique visual experiences through composing a complex interplay between the content and style of an image.  ...  The class of Deep Neural Networks that are most powerful in image processing tasks are called Convolutional Neural Networks.  ... 
doi:10.1167/16.12.326 fatcat:difs3cqj55cq5gfjkpyedwvv2m

Informing Artificial Intelligence Generative Techniques using Cognitive Theories of Human Creativity [article]

Steve DiPaola, Liane Gabora, Graeme McCaig
2018 arXiv   pre-print
Using an original synthesis of Deep Dream-based convolutional neural networks and cognitive based computational art rendering systems, we show how honing theory, intrinsic motivation, and the notion of  ...  Conversely, we discuss how explorations in deep learn-ing convolutional neural net generative systems can inform our understanding of human creativity.  ...  Acknowledgments This research was supported in part by a grant to Gabora from the Natural Sciences and Engineering Research Council of Canada and SSHRC grant to DiPaola.  ... 
arXiv:1812.05556v1 fatcat:avsbibrhvnggzbfw5eonbpgec4

Informing artificial intelligence generative techniques using cognitive theories of human creativity

Steve DiPaola, Liane Gabora, Graeme McCaig
2018 Procedia Computer Science  
Using an original synthesis of DeepDream-based convolutional neural networks and cognitive based computational art rendering systems, we show how honing theory, intrinsic motivation, and the notion of  ...  Conversely, we discuss how explorations in deep learning convolutional neural net generative systems can inform our understanding of human creativity.  ...  Acknowledgments This research was supported in part by a grant to Gabora from the Natural Sciences and Engineering Research Council of Canada and SSHRC grant to DiPaola.  ... 
doi:10.1016/j.procs.2018.11.024 fatcat:rrm4bjj7w5bobfuzedahywwp3a

Neural style transfer

Amir Semmo, Tobias Isenberg, Jürgen Döllner
2017 Proceedings of the Symposium on Non-Photorealistic Animation and Rendering - NPAR '17  
ACKNOWLEDGMENTS We would like to thank the anonymous reviewers for their comments and suggestions on how to improve the paper.  ...  This work was partly funded by the Federal Ministry of Education and Research (BMBF), Germany, for the AVA project 01IS15041B.  ...  According to Leon Gatys in his talk at CVPR 2016 on "Image Style Transfer Using Convolutional Neural Networks" (Gatys et al. 2016b) . Stephen Merity. 2016.  ... 
doi:10.1145/3092919.3092920 dblp:conf/npar/SemmoID17 fatcat:3udzwr4mcndozpawlr2q34b47i

Deep Convolutional Networks as Models of Generalization and Blending Within Visual Creativity [article]

Graeme McCaig, Steve DiPaola, Liane Gabora
2019 arXiv   pre-print
We examine two recent artificial intelligence (AI) based deep learning algorithms for visual blending in convolutional neural networks (Mordvintsev et al. 2015, Gatys et al. 2015).  ...  of their output.  ...  Our DS implementation is based on: https://github.com/fzliu/style-transfer .  ... 
arXiv:1610.02478v2 fatcat:5wdgmhbh3zgnbp2a36k3q26bju

Can We Teach Computers to Understand Art? Domain Adaptation for Enhancing Deep Networks Capacity to De-Abstract Art [article]

Mihai Badea, Corneliu Florea, Laura Florea, Constantin Vertan
2017 arXiv   pre-print
In this paper we address the problem of recognizing the genre (subject) in digitized paintings using Convolutional Neural Networks (CNN) as part of the more general dealing with abstract and/or artistic  ...  Surprisingly, the most efficient domain adaptation is not the neural style transfer. Finally, the paper provides an experiment-based assessment of the abstraction level that CNNs are able to achieve.  ...  The work was supported by grants of the Romanian National Authority for Scientific Research and Innovation, CNCS UEFISCDI, number PN-II-RU-TE-2014-4-0733 and respectively, CCCDI-UEFISCDI, project number  ... 
arXiv:1712.03727v1 fatcat:64iht2a5ubbntkmuvkxfsdjtuy

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.  ...  One paper tested YOLO, a conv-net based model, on a range of European paintings [14] . Figure 2 shows some of the network's outputs.  ... 
arXiv:1911.07068v1 fatcat:fy2xtl2pzffednzgdaqk3yvmde

DSSESKN: A depthwise separable squeeze-and-excitation selective kernel network for art image classification

Shaojie Zhang
2021 EAI Endorsed Transactions on Scalable Information Systems  
Image classification is one of the key technologies of content-based image retrieval, and it is also the focus and hotspot of image content analysis research in recent years.  ...  The convolution kernel on the branch of DSSESKN module is used to extract the global feature and local detail features of the input image.  ...  Art image classification based on DSSESKN DSSESKN module In this paper, DSSESKN combines the SE module and the SK module to better enhance the overall style features and local detail features of the  ... 
doi:10.4108/eai.26-11-2021.172304 fatcat:rp2pflhc6bfunakww6lysmhwdi

Image Style Transfer Using Convolutional Neural Networks

Leon A. Gatys, Alexander S. Ecker, Matthias Bethge
2016 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)  
Rendering the semantic content of an image in different styles is a difficult image processing task.  ...  We introduce A Neural Algorithm of Artistic Style that can separate and recombine the image content and style of natural images.  ...  on a number of layers of the Convolutional Neural Network.  ... 
doi:10.1109/cvpr.2016.265 dblp:conf/cvpr/GatysEB16 fatcat:44srhalyrfho3bpirsyzohhckq
« Previous Showing results 1 — 15 out of 959 results