Filters








5,205 Hits in 4.4 sec

Stroke Controllable Fast Style Transfer with Adaptive Receptive Fields [article]

Yongcheng Jing, Yang Liu, Yezhou Yang, Zunlei Feng, Yizhou Yu, Dacheng Tao, Mingli Song
2018 arXiv   pre-print
The Fast Style Transfer methods have been recently proposed to transfer a photograph to an artistic style in real-time.  ...  We propose a StrokePyramid module to endow the network with adaptive receptive fields, and two training strategies to achieve faster convergence and augment new stroke sizes upon a trained model respectively  ...  To this end, we propose a StrokePyramid module to endow the network with adaptive receptive fields and different stroke sizes are learned with different receptive fields.  ... 
arXiv:1802.07101v4 fatcat:hvq27gav2fg4zfnle4tyjygt4m

Interactive Multi-level Stroke Control for Neural Style Transfer [article]

Max Reimann and Benito Buchheim and Amir Semmo and Jürgen Döllner and Matthias Trapp
2021 arXiv   pre-print
To this end, we propose a novel stroke-adaptive feed-forward style transfer network, that enables control over stroke size and intensity and allows a larger range of edits than current approaches.  ...  Our approach empowers users to create many novel results that are not possible with current mobile neural style transfer apps.  ...  The stroke size parameter λ S effectively controls the receptive field size of the stroke branch (Section III-D). 2) Stroke-Intensity Control: Based on instance normalization, Dumoulin et al.  ... 
arXiv:2106.13787v1 fatcat:ysvqmbeo6fepppouwrwguyfraq

Attention-Aware Multi-Stroke Style Transfer

Yuan Yao, Jianqiang Ren, Xuansong Xie, Weidong Liu, Yong-Jin Liu, Jun Wang
2019 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)  
Neural style transfer has drawn considerable attention from both academic and industrial field.  ...  In this paper, we tackle these limitations by developing an attention-aware multi-stroke style transfer model.  ...  Based on the analysis of how receptive field influences stroke size in [8] , we note that larger patch size leads to larger receptive field and style stroke accordingly.  ... 
doi:10.1109/cvpr.2019.00156 dblp:conf/cvpr/YaoRX0LW19 fatcat:xdtqe4gdtzgipft2sringb7s5u

Attention-aware Multi-stroke Style Transfer [article]

Yuan Yao, Jianqiang Ren, Xuansong Xie, Weidong Liu, Yong-Jin Liu, Jun Wang
2019 arXiv   pre-print
Neural style transfer has drawn considerable attention from both academic and industrial field.  ...  In this paper, we tackle these limitations by developing an attention-aware multi-stroke style transfer model.  ...  Based on the analysis of how receptive field influences stroke size in [8] , we note that larger patch size leads to larger receptive field and style stroke accordingly.  ... 
arXiv:1901.05127v1 fatcat:z2oeazoq4na6rky6hk7lnhule4

Arbitrary Style Transfer via Multi-Adaptation Network [article]

Yingying Deng, Fan Tang, Weiming Dong, Wen Sun, Feiyue Huang, Changsheng Xu
2020 arXiv   pre-print
A desired style transfer, given a content image and referenced style painting, would render the content image with the color tone and vivid stroke patterns of the style painting while synchronously maintaining  ...  Arbitrary style transfer is a significant topic with research value and application prospect.  ...  (b) With style and content disentanglement, the content structures are more visible. Figure 7 : 7 Comparison of stylized results with different receptive field size.  ... 
arXiv:2005.13219v2 fatcat:6zfpd3qdbjcfvi2wgrccsfd4o4

Controllable Artistic Text Style Transfer via Shape-Matching GAN [article]

Shuai Yang, Zhangyang Wang, Zhaowen Wang, Ning Xu, Jiaying Liu, Zongming Guo
2019 arXiv   pre-print
Recent style transfer methods have considered texture control to enhance usability. However, controlling the stylistic degree in terms of shape deformation remains an important open challenge.  ...  In this paper, we present the first text style transfer network that allows for real-time control of the crucial stylistic degree of the glyph through an adjustable parameter.  ...  [17] proposed a stroke-controllable neural style transfer network (SC-NST) with adaptive receptive fields for stroke size control.  ... 
arXiv:1905.01354v2 fatcat:7ne4xt5l4jeppfzcldkpzevcw4

Dynamic Instance Normalization for Arbitrary Style Transfer

Yongcheng Jing, Xiao Liu, Yukang Ding, Xinchao Wang, Errui Ding, Mingli Song, Shilei Wen
2020 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
automatic spatial-stroke control.  ...  for fast inference.  ...  In deformable convolutions, the receptive fields and sampling locations can be adaptively adjusted according to the foreground objects' shape and scale.  ... 
doi:10.1609/aaai.v34i04.5862 fatcat:ma5rzszv5rbvhdi5ikj3n533qi

Dynamic Instance Normalization for Arbitrary Style Transfer [article]

Yongcheng Jing, Xiao Liu, Yukang Ding, Xinchao Wang, Errui Ding, Mingli Song, Shilei Wen
2019 arXiv   pre-print
automatic spatial-stroke control.  ...  for fast inference.  ...  In deformable convolutions, the receptive fields and sampling locations can be adaptively adjusted according to the foreground objects' shape and scale.  ... 
arXiv:1911.06953v1 fatcat:5by3bk6gxvhmljrhahhj3gsjsq

Neural Style Transfer: A Review [article]

Yongcheng Jing, Yezhou Yang, Zunlei Feng, Jingwen Ye, Yizhou Yu, Mingli Song
2018 arXiv   pre-print
This process of using CNNs to render a content image in different styles is referred to as Neural Style Transfer (NST).  ...  A list of papers discussed in this review, corresponding codes, pre-trained models and more comparison results are publicly available at https://github.com/ycjing/Neural-Style-Transfer-Papers.  ...  The core component of their algorithm is a StrokePyramid module, which learns different stroke sizes with adaptive receptive fields.  ... 
arXiv:1705.04058v7 fatcat:5yhckjrfargjnnhjihjiwzjiz4

Style is a Distribution of Features [article]

Eddie Huang, Sahil Gupta
2020 arXiv   pre-print
Neural style transfer (NST) is a powerful image generation technique that uses a convolutional neural network (CNN) to merge the content of one image with the style of another.  ...  Contemporary methods of NST use first or second order statistics of the CNN's features to achieve transfers with relatively little computational cost.  ...  . • Thanks to Bennett Ip for helping us with the initial developments of this project.  ... 
arXiv:2007.13010v1 fatcat:2avg4xcwqbcf3mj2mckbpxqwry

Style Mixer: Semantic‐aware Multi‐Style Transfer Network

Zixuan Huang, Jinghuai Zhang, Jing Liao
2019 Computer graphics forum (Print)  
Recent neural style transfer frameworks have obtained astonishing visual quality and flexibility in Single-style Transfer (SST), but little attention has been paid to Multi-style Transfer (MST) which refers  ...  to simultaneously transferring multiple styles to the same image.  ...  And we acknowledge to the authors of our image and style examples. This work was partly supported by CityU start-up grant 7200607 and Hong Kong ECS grant 21209119.  ... 
doi:10.1111/cgf.13853 fatcat:ss7kr2l2gfbhxabonw4utoyj24

Fast Image Processing with Fully-Convolutional Networks [article]

Qifeng Chen, Jia Xu, Vladlen Koltun
2017 arXiv   pre-print
We evaluate the presented approach on ten advanced image processing operators, including multiple variational models, multiscale tone and detail manipulation, photographic style transfer, nonlocal dehazing  ...  Style transfer. This operator transfers the photographic style of a reference image to the input image [1] .  ...  This configuration benefits from a receptive field of 513 × 513 versus the 257 × 257 receptive field of CAN24.  ... 
arXiv:1709.00643v1 fatcat:4dzvtbeucrhmvdmgk7jpdclm5m

Channel Decomposition into Painting Actions [article]

Shih-Chieh Su
2019 arXiv   pre-print
To behave like the human painter, these actions are driven by the cost simulating the hand movement, the paint color change, the stroke shape and the stroking style.  ...  The proposed painting system introduces a variety of extensions in artistic styles, based on the chosen parameters.  ...  Leveraging the channel depth of the generator networks, the proposed strategy strokes through the same channels continuously over the regions with high receptive field response.  ... 
arXiv:1908.04694v4 fatcat:nxcbnpwopjaa7cjsnzbuuynhyu

A Novel Method for Automatic Camouflage Pattern Synthesize

Xinjian Wei, Guangxu Li, Kaidi Wang
2021 IEEE Access  
In the conventional style transfer algorithm, controlling stroke size in style conversion is still a daunting task.  ...  Lingchen Yang et al. proposed a recurrent convolutional neural network to control the stroke size in style transfer in [35] .  ...  enhance the adaptability of camouflage patterns.  ... 
doi:10.1109/access.2021.3077258 fatcat:zsmvoajty5c73czq5nlcvfutry

Applying visual domain style transfer and texture synthesis techniques to audio: insights and challenges

Muhammad Huzaifah bin Md Shahrin, Lonce Wyse
2019 Neural computing & applications (Print)  
These ideas also prompt an exploration of audio texture synthesis with architectural variants for extensions to infinite textures, multi-textures, parametric control of receptive fields and the constant-Q  ...  Style transfer is a technique for combining two images based on the activations and feature statistics in a deep learning neural network architecture.  ...  in turn changes the effective receptive field of neural units in the CNN.  ... 
doi:10.1007/s00521-019-04053-8 fatcat:yeq2q37rgnbfhd2sy2333dsi3m
« Previous Showing results 1 — 15 out of 5,205 results