Filters








11,840 Hits in 4.8 sec

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)  
In this paper, we tackle these limitations by developing an attention-aware multi-stroke style transfer model.  ...  Neural style transfer has drawn considerable attention from both academic and industrial field.  ...  Conclusion In this paper, we propose an attention-aware multi-stroke style transfer model for arbitrary styles.  ... 
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
In this paper, we tackle these limitations by developing an attention-aware multi-stroke style transfer model.  ...  Neural style transfer has drawn considerable attention from both academic and industrial field.  ...  More results of our attention-aware multi-stroke style transfer method (Set 2).  ... 
arXiv:1901.05127v1 fatcat:z2oeazoq4na6rky6hk7lnhule4

Anisotropic Stroke Control for Multiple Artists Style Transfer [article]

Xuanhong Chen, Xirui Yan, Naiyuan Liu, Ting Qiu, Bingbing Ni
2020 arXiv   pre-print
To circumvent this issue, we propose a Stroke Control Multi-Artist Style Transfer framework.  ...  On the one hand, we develop a multi-condition single-generator structure which first performs multi-artist style transfer.  ...  Our model is able to perform multi-artist style transfer within one model, while well preserving semantic information through anisotropic style-stroke controlling.  ... 
arXiv:2010.08175v1 fatcat:l7hvctou5vewhdvo2nufrt3yaa

SAFIN: Arbitrary Style Transfer With Self-Attentive Factorized Instance Normalization [article]

Aaditya Singh, Shreeshail Hingane, Xinyu Gong, Zhangyang Wang
2021 arXiv   pre-print
Artistic style transfer aims to transfer the style characteristics of one image onto another image while retaining its content.  ...  We also develop a novel base network composed of Wavelet Transform for multi-scale style transfer, which when combined with SAFIN, produces visually appealing results with lesser unwanted textures.  ...  In addition, we develop a novel base network composed of Wavelet Transform for multi-scale style transfer.  ... 
arXiv:2105.06129v2 fatcat:bf2zohg33vco3cchb7vdwihwdi

StyTr^2: Image Style Transfer with Transformers [article]

Yingying Deng and Fan Tang and Weiming Dong and Chongyang Ma and Xingjia Pan and Lei Wang and Changsheng Xu
2022 arXiv   pre-print
We also analyze the deficiency of existing positional encoding methods and propose the content-aware positional encoding (CAPE), which is scale-invariant and more suitable for image style transfer tasks  ...  Following the encoders, a multi-layer transformer decoder is adopted to stylize the content sequence according to the style sequence.  ...  AAMS [18] consists of a self-attention autoencoder capturing the main structures of the content images, and a multi-stroke style transfer model based on patch-swap [59] .  ... 
arXiv:2105.14576v3 fatcat:22kkoja5ajhrzniasqilbj76r4

Fashion Editing With Adversarial Parsing Learning

Haoye Dong, Xiaodan Liang, Yixuan Zhang, Xujie Zhang, Xiaohui Shen, Zhenyu Xie, Bowen Wu, Jian Yin
2020 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)  
A new attention normalization layer is further applied at multiple scales in the decoder of the inpainting network to enhance the quality of the synthesized image.  ...  FE-GAN consists of two modules: 1) a free-form parsing network that learns to control the human parsing generation by manipulating sketch and color; 2) a parsing-aware inpainting network that renders detailed  ...  For style transfer tasks [26] , affine parameters are spatially-invariant since they only control the global style of the output images.  ... 
doi:10.1109/cvpr42600.2020.00814 dblp:conf/cvpr/DongLZZSXW020 fatcat:kre4h64vc5dohczeiboc3unlyi

Fashion Editing with Adversarial Parsing Learning [article]

Haoye Dong, Xiaodan Liang, Yixuan Zhang, Xujie Zhang, Zhenyu Xie, Bowen Wu, Ziqi Zhang, Xiaohui Shen, Jian Yin
2019 arXiv   pre-print
A new attention normalization layer is further applied at multiple scales in the decoder of the inpainting network to enhance the quality of the synthesized image.  ...  FE-GAN consists of two modules: 1) a free-form parsing network that learns to control the human parsing generation by manipulating sketch and color; 2) a parsing-aware inpainting network that renders detailed  ...  For style transfer tasks [26, 31] , affine parameters are spatially-invariant since they only control the global style of the output images.  ... 
arXiv:1906.00884v2 fatcat:3i2kxaal7rh65dh7kw6absgila

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  ...  We first improve the existing SST backbone network by introducing a novel multi-level feature fusion module and a patch attention module to achieve better semantic correspondences and preserve richer style  ...  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

Semantic Context-Aware Image Style Transfer

Yi-Sheng Liao, Chun-Rong Huang
2022 IEEE Transactions on Image Processing  
To solve the semantic matching problem and guide the semantic image style transfer based on matched regions, we propose a novel semantic context-aware image style transfer method by performing semantic  ...  To achieve semantic context-aware style transfer, a hierarchical local-to-global network architecture, which contains two sub-networks including the local context network and the global context network  ...  To enable local awareness of the content image, Yao et al. [21] develop an attention-aware multi-stroke (AAMS) model for arbitrary style transfer.  ... 
doi:10.1109/tip.2022.3149237 pmid:35143399 fatcat:3od3iqpyizfk5c6ssa6rsler5i

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  ...  Various qualitative and quantitative experiments demonstrate that the proposed multi-adaptation network leads to better results than the state-of-the-art style transfer methods.  ...  [28] achieved multi-stroke style results using self-attention mechanism.  ... 
arXiv:2005.13219v2 fatcat:6zfpd3qdbjcfvi2wgrccsfd4o4

Domain-Aware Universal Style Transfer [article]

Kibeom Hong, Seogkyu Jeon, Huan Yang, Jianlong Fu, Hyeran Byun
2021 arXiv   pre-print
Moreover, we introduce a unified framework with domain-aware skip connection to adaptively transfer the stroke and palette to the input contents guided by the domainness indicator.  ...  To overcome this limitation, we propose a unified architecture, Domain-aware Style Transfer Networks (DSTN) that transfer not only the style but also the property of domain (i.e., domainness) from a given  ...  We first describe the proposed auto-encoder with domain-aware skip connection for multi-domain style transfer.  ... 
arXiv:2108.04441v3 fatcat:aa2y2bmxdjfylhh3w6nysk3b5y

Pseudo-Supervised Learning for Semantic Multi-Style Transfer

Saehun Kim, Jeonghyeok Do, Munchurl Kima
2021 IEEE Access  
Moreover, to embrace the multi-styles of various objects into a single generator, we design the SMSTnet with channel attentions in conjunction with a discriminator dedicated to our pseudo-supervised learning  ...  From this, our framework can provide the semantic mappings of multi-style objects.  ...  SEMANTIC MULTI-STYLE TRANSFER An example domain of the object-to-object multi-style transfer is the anime style domain.  ... 
doi:10.1109/access.2021.3049637 fatcat:sm7p2xyb6vdghmi2lmstrjtlwi

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
We present StyleTune, a mobile app for interactive multi-level control of neural style transfers that facilitates creative adjustments of style elements and enables high output fidelity.  ...  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.  ...  Yao et al. incorporate self-attention into multi-stroke transfer [19] .  ... 
arXiv:2106.13787v1 fatcat:ysvqmbeo6fepppouwrwguyfraq

DRB-GAN: A Dynamic ResBlock Generative Adversarial Network for Artistic Style Transfer [article]

Wenju Xu and Chengjiang Long and Ruisheng Wang and Guanghui Wang
2021 arXiv   pre-print
In the style encoding network, a style class-aware attention mechanism is used to attend the style feature representation for generating the style codes.  ...  Moreover, the style collection conditional discriminator is designed to equip our DRB-GAN model with abilities for both arbitrary style transfer and collection style transfer during the training stage.  ...  A style class-aware attention mechanism is employed to recalibrate the style code.  ... 
arXiv:2108.07379v3 fatcat:vlct2cwobjcnje66td6b65fxy4

Arbitrary Video Style Transfer via Multi-Channel Correlation [article]

Yingying Deng, Fan Tang, Weiming Dong, Haibin Huang, Chongyang Ma, Changsheng Xu
2021 arXiv   pre-print
Video style transfer is getting more attention in AI community for its numerous applications such as augmented reality and animation productions.  ...  Towards this end, we propose Multi-Channel Correction network (MCCNet), which can be trained to fuse the exemplar style features and input content features for efficient style transfer while naturally  ...  Yao et al. (2019) proposed an attention-aware multi-stroke style transfer (AAMS) model by adopting selfattention to a style swap-based image transfer method, which highly relies on the accuracy of the  ... 
arXiv:2009.08003v2 fatcat:xlb6rhhrwjhv5blr6gjig7zwim
« Previous Showing results 1 — 15 out of 11,840 results