Filters








6,045 Hits in 5.5 sec

A Generative Adversarial Network for AI-Aided Chair Design

Zhibo Liu, Feng Gao, Yizhou Wang
2019 2019 IEEE Conference on Multimedia Information Processing and Retrieval (MIPR)  
We present a method for improving human design of chairs.  ...  It consists of an image synthesis module, which learns the underlying distribution of training dataset, a super-resolution module, which improve quality of generated image and human involvements.  ...  Image to Image Translation Image to Image translation methods have been successfully applied for style transfer and image super-resolution, which can be used as a powerful tool for auxiliary design.For  ... 
doi:10.1109/mipr.2019.00098 dblp:conf/mipr/LiuGW19 fatcat:wc5ijncuynhhxgt3an5n2e5vs4

Deep learning approaches to pattern extraction and recognition in paintings and drawings: an overview

Giovanna Castellano, Gennaro Vessio
2021 Neural computing & applications (Print)  
Recent advances in deep learning and computer vision, coupled with the growing availability of large digitized visual art collections, have opened new opportunities for computer science researchers to  ...  Another way to perform image-to-image translation, particularly in the opposite direction, is to use the wellknown neural style transfer technique originally proposed by Gatys et al. [93] .  ...  Unfortunately, while effective in transferring artistic styles, this method usually works poorly in the opposite direction, i.e. when asked to translate artworks into photo-realistic images.  ... 
doi:10.1007/s00521-021-05893-z fatcat:elqzw3hzbzgodotie6ndih537u

Manipulating Attributes of Natural Scenes via Hallucination [article]

Levent Karacan, Zeynep Akata, Aykut Erdem, Erkut Erdem
2019 arXiv   pre-print
As the proposed framework hallucinates what the scene will look like, it does not require any reference style image as commonly utilized in most of the appearance or style transfer approaches.  ...  Once the scene is hallucinated with the given attributes, the corresponding look is then transferred to the input image while preserving the semantic details intact, giving a photo-realistic manipulation  ...  We would like to thank NVIDIA Corporation for the donation of GPUs used in this research. This work has been partially funded by the DFG-EXC-Nummer 2064/1-Projektnummer 390727645.  ... 
arXiv:1808.07413v3 fatcat:74xfm7dieram5ex466qdjlzjmu

Unified Style Transfer [article]

Guanjie Huang, Hongjian He, Xiang Li, Xingchen Li, Ziang Liu
2021 arXiv   pre-print
With the introduction of a generative model for internal style representation, UST can transfer images in two approaches, i.e., Domain-based and Image-based, simultaneously.  ...  At the same time, a new philosophy based on the human sense of art and style distributions for evaluating the transfer model is presented and demonstrated, called Statistical Style Analysis.  ...  The conditional GAN is used to handle multistyle/multi-domain style transfer [10] for single image input.  ... 
arXiv:2110.10481v1 fatcat:qsjsmuyvyzfyzb5qkksfxqg5r4

Learning to Generate Multiple Style Transfer Outputs for an Input Sentence

Kevin Lin, Ming-Yu Liu, Ming-Ting Sun, Jan Kautz
2020 Proceedings of the Fourth Workshop on Neural Generation and Translation  
We then combine the content code with the style code for generating a style transfer output.  ...  Extensive experimental results with comparisons to several text style transfer approaches on multiple public datasets using a diverse set of performance metrics validate effectiveness of the proposed approach  ...  Acknowledgement We would like to thank the anonymous reviewers for their constructive comments. We thank NVIDIA for the donation of the GPU used for this research.  ... 
doi:10.18653/v1/2020.ngt-1.2 dblp:conf/aclnmt/LinLSK20 fatcat:zaxyhz5pfjdjzbjqkndfcpdfhq

Learning to Caricature via Semantic Shape Transform

Wenqing Chu, Wei-Chih Hung, Yi-Hsuan Tsai, Yu-Ting Chang, Yijun Li, Deng Cai, Ming-Hsuan Yang
2021 International Journal of Computer Vision  
Specifically, we predict pixel-wise semantic correspondences and perform image warping on the input photo to achieve dense shape transformation.  ...  The images or other third party material in this article are included in the article's Creative Commons licence, unless indicated otherwise in a credit line to the material.  ...  If material is not included in the article's Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly  ... 
doi:10.1007/s11263-021-01489-1 fatcat:5xoghtstrvbfflfuqrz5sgasgm

Artistic Object Recognition by Unsupervised Style Adaptation [article]

Christopher Thomas, Adriana Kovashka
2018 arXiv   pre-print
We show how such artificial labeled source domains can be generated automatically through the use of style transfer techniques, using diverse target images to represent the style in the target domain.  ...  Our experiments show that our approach, though conceptually simple, significantly improves the accuracy that existing domain adaptation techniques obtain for artistic object recognition.  ...  Acknowledgement: This material is based upon work supported by the National Science Foundation under NSF CISE Award No. 1566270.  ... 
arXiv:1812.11139v1 fatcat:uk73pqrywbeutjjcg4byy76qku

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
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.  ...  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  ...  The authors would like to thank NVIDIA Corporation for donating the Tesla K40c GPU that helped run the experimental setup for this research.  ... 
arXiv:1712.03727v1 fatcat:64iht2a5ubbntkmuvkxfsdjtuy

StyleBlit: Fast Example-Based Stylization with Local Guidance [article]

Daniel Sýkora and Ondřej Jamriška and Jingwan Lu and Eli Shechtman
2018 arXiv   pre-print
Our technique is especially suitable for style transfer applications that use local guidance - descriptive guiding channels containing large spatial variations.  ...  Local guidance encourages transfer of content from the source exemplar to the target image in a semantically meaningful way.  ...  [SED16] SELIM A., ELGHARIB M., DOYLE L.: Painting style transfer for head portraits using convolutional neural networks. ACM Transactions on Graphics 35, 4 (2016), 129.  ... 
arXiv:1807.03249v1 fatcat:ayda2nmibzdw7kiw2p7mwp6wku

Large-scale Hierarchical Alignment for Data-driven Text Rewriting [article]

Nikola I. Nikolov, Richard H.R. Hahnloser
2019 arXiv   pre-print
We propose a simple unsupervised method for extracting pseudo-parallel monolingual sentence pairs from comparable corpora representative of two different text styles, such as news articles and scientific  ...  We demonstrate the effectiveness of LHA on automatic benchmarks for alignment (Section 4), as well as extrinsically, by training neural machine translation (NMT) systems on two style transfer tasks: text  ...  We therefore use it as the default approach for the following experiments on style transfer.  ... 
arXiv:1810.08237v2 fatcat:w6cifljdo5gulmypgasdo3yp2e

A survey on Image Data Augmentation for Deep Learning

Connor Shorten, Taghi M. Khoshgoftaar
2019 Journal of Big Data  
training, generative adversarial networks, neural style transfer, and meta-learning.  ...  Deep neural networks have been successfully applied to Computer Vision tasks such as image classification, object detection, and image segmentation thanks to the development of convolutional neural networks  ...  Image-to-image translation has many potential uses in Data Augmentation. Neural Style Transfer uses neural layers to translate images into new styles.  ... 
doi:10.1186/s40537-019-0197-0 fatcat:yrzshu3sgje27p2j7acxwfmvva

Neural 3D Mesh Renderer [article]

Hiroharu Kato, Yoshitaka Ushiku, Tatsuya Harada
2017 arXiv   pre-print
Additionally, we perform gradient-based 3D mesh editing operations, such as 2D-to-3D style transfer and 3D DeepDream, with 2D supervision for the first time.  ...  However, it is not straightforward to model a polygon mesh from 2D images using neural networks because the conversion from a mesh to an image, or rendering, involves a discrete operation called rasterization  ...  Acknowledgment This work was partially funded by ImPACT Program of Council for Science, Technology and Innovation (Cabinet Office, Government of Japan) and partially supported by JST CREST Grant Number  ... 
arXiv:1711.07566v1 fatcat:tb43y4unhfbyforqazqmptudfe

Supervised Symbolic Music Style Translation Using Synthetic Data [article]

Ondřej Cífka, Umut Şimşekli, Gaël Richard
2019 arXiv   pre-print
Research on style transfer and domain translation has clearly demonstrated the ability of deep learning-based algorithms to manipulate images in terms of artistic style.  ...  In view of this data generation scheme, we propose an encoder-decoder model for translating symbolic music accompaniments between a number of different styles.  ...  Image style transfer using convolutional neural This research is supported by the European Union’s Hori- networks.  ... 
arXiv:1907.02265v1 fatcat:mlpc54kq45bndml6ds3gibfhvu

Art2Real: Unfolding the Reality of Artworks via Semantically-Aware Image-to-Image Translation [article]

Matteo Tomei, Marcella Cornia, Lorenzo Baraldi, Rita Cucchiara
2019 arXiv   pre-print
Experimental results show that the proposed technique leads to increased realism and to a reduction in domain shift, which improves the performance of pre-trained architectures for classification, detection  ...  Our architecture can generate natural images by retrieving and learning details from real photos through a similarity matching strategy which leverages a weakly-supervised semantic understanding of the  ...  Another way of performing imageto-image translation is that of neural style transfer methods [7, 8, 18, 14, 39] , in which a novel image is synthesized by combining the content of one image with the style  ... 
arXiv:1811.10666v3 fatcat:fmhdvwafezfzxgctskprte33ke

Art2Real: Unfolding the Reality of Artworks via Semantically-Aware Image-To-Image Translation

Matteo Tomei, Marcella Cornia, Lorenzo Baraldi, Rita Cucchiara
2019 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)  
Experimental results show that the proposed technique leads to increased realism and to a reduction in domain shift, which improves the performance of pre-trained architectures for classification, detection  ...  Our architecture can generate natural images by retrieving and learning details from real photos through a similarity matching strategy which leverages a weakly-supervised semantic understanding of the  ...  Another way of performing imageto-image translation is that of neural style transfer methods [7, 8, 18, 14, 39] , in which a novel image is synthesized by combining the content of one image with the style  ... 
doi:10.1109/cvpr.2019.00600 dblp:conf/cvpr/TomeiCBC19 fatcat:kyx5vakxfrcmtbbxlto6marbqa
« Previous Showing results 1 — 15 out of 6,045 results