Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
Skip to main content
Springer Nature Link
Log in

Research on style transfer for multiple regions

  • Published:
Multimedia Tools and Applications Aims and scope Submit manuscript

Abstract

The exciting method of creating unique visual experiences through composing a complex interplay between the content and style of an image has been extended to art works, creative design, video processing and other fields. Image style transfer technology is used to create images colorful styles automatically. Most of the existing researches focus on the style transfer of the whole image or a single region in the image, which is inevitably not adequate for practical applications. In this work, we introduce an approach of differential stylization for image different areas. Considering the human visual attention mechanism, the saliency regions in the training image data set are labeled, and the salient regions are trained in the semantic segmentation model. The structure of the neural style transfer model is simplified to improve the operation efficiency. In our approach, each local target region in the image is stylized evenly and carefully. Different regions are well integrated to achieve more realistic and pleasing effect, while more dominant operation efficiency is achieved. We separately perform experiments with the Cityscapes and the Microsoft COCO 2017 database. The performance is also compared with some reported methods and shown improved, while considering the accuracy and efficiency as performance metrics.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13

Similar content being viewed by others

References

  1. Benedetti L, Winnemoller MH, Corsini, and Scopigno R (2014) Painting with bob: Assisted creativity for novices[C]. In Proc. UIST

  2. Castillo C, De S, Han XT, et al. (2017) Son of Zorn’s lemma: targeted style transfer using instance-aware semantic segmentation [C]//Proceedings of 2017 IEEE International Conference on Acoustics Speech, and Signal Processing. New Orleans, LA: IEEE : 1348–1352. https://doi.org/10.1109/ICASSP.2017.7952376

  3. Champandard AJ (2016) Semantic Style Transfer and Turning Two-Bit Doodles into Fine Artworks. arXiv:1603.01768 [CS], arXiv: 1603.01768

  4. Champandard AJ (2016) Semantic style transfer and turning two-bit doodles into fine artworks [J]. arXiv preprint arXiv:1603.01768

  5. Chen T Q, Schmidt M (2016) Fast patch-based style transfer of arbitrary style[J]. arXiv preprint arXiv:1612.04337

  6. Chen LC, Zhu Y, Papandreou G, et al. (2018)Encoder-decoder with atrous separable convolution for semantic image segmentation [C]//proc of European conference on computer vision (ECCV)

    Google Scholar 

  7. Choi HC (2020) Unbiased image style transfer[J]. IEEE Access 8:196600–196608

    Article  Google Scholar 

  8. Faridul HS, Pouli T, Chamaret C, Stauder J, Reinhard E, Kuzovkin D, Tremeau A (2016) Colour mapping: a review of recent methods, extensions and applications[J]. Computer Graphics Forum 35(1):59–88

    Article  Google Scholar 

  9. Gatys LA, Ecker AS, Bethge M (2015) A neural algorithm of artistic style[J]. arXiv preprint arXiv:1508.06576

  10. Gatys LA, Alexander S Ecker, and Matthias Bethge (2015) Texture synthesis using convolutional neural networks[C]. In NIPS

  11. Gatys LA, Alexander S Ecker, and Matthias Bethge (2016) Image style transfer using convolutional neural networks[C]. In CVPR

  12. Gatys LA, Ecker AS, Bethge M (2016) Image style transfer using convolutional neural networks[C]. In Proc, CVPR

    Book  Google Scholar 

  13. Gatys LA, Ecker AS, Bethge M (2017) Controlling Perceptual Factors in Neural Style Transfer[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition : 3730–3738

  14. Heeger DJ and Bergen JR (1995)Pyramid-based Texture Analysis/Synthesis [C]. In Proceedings of the 22Nd Annual Conference on Computer Graphics and Interactive Techniques, SIGGRAPH ‘95, pages 229–238, New York, NY, USA. ACM

  15. Hertzmann A (1998) Painterly rendering with curved brush strokes of multiple sizes[C]//Proceedings of the 25th annual conference on Computer graphics and interactive techniques : 453–460

  16. Hertzmann A, Jacobs C E, Oliver N, et al. (2001) Image analogies[C]//Proceedings of the 28th annual conference on Computer graphics and interactive techniques : 327–340

  17. Hu C, Ding YD, Gao YZ (2020) Artistic Text Style Transfer based on Generative Adversarial Networks[C]//Proceedings of the 7th International Forum on Electrical Engineering and Automation : 451–455

  18. Huang X, Belongie S (2017) Arbitrary style transfer in real-time with adaptive instance normalization [C]//Proceedings of the IEEE International Conference on Computer Vision : 1501–1510

  19. Jin ZG, Zhou MR (2021) Research on Image Style Transfer Algorithm Based on Convolutional Neural Networks [J]. Journal of Hefei University (Comprehensive Edition) 38(2):27–33

    Google Scholar 

  20. Johnson J, Alexandre Alahi, and Li Fei-Fei(2016) Perceptual losses for real-time style transfer and super-resolution[C]. In ECCV

    Book  Google Scholar 

  21. Johnson J, Alahi A, Fei-Fei L (2016) Perceptual Losses for Real-Time Style Transfer and Super-Resolution[J]. Computer Science, 14th European Conference on Computer Vision (ECCV)

  22. Julesz B (1962) Visual Pattern Discrimination. IRE Trans Inf Theory[J], 8(2)

  23. Kalnins D, Markosian L, Meier BJ, Kowalski MA, Lee JC, Davidson PL, Webb M, Hughes JF, and Finkelstein A (2002) Drawing strokes directly on 3d models. ACM Trans Graph 21(3)

  24. Kolliopoulos A (2005) Image segmentation for stylized non-photorealistic rendering and animation[M]. University of Toronto

  25. Li C and Wand M (2016) Precomputed real-time texture synthesis with markovian generative adversarial networks[C]. In ECCV

  26. Li C and Wand M (2016) Combining markov random fields and convolutional neural networks for image synthesis[C]. In Proc CVPR

  27. Li C, Wand M (2016) Combining markov random fields and convolutional neural networks for image synthesis[C]. In Proc, CVPR

    Book  Google Scholar 

  28. Li Y, Wang N, Liu J, Hou X (2017) Demystifying neural style transfer. arXiv preprint arXiv:1701.01036

    Google Scholar 

  29. Li SH, Xu XX, Nie LQ, et al. (2017)Laplacian-Steered Neural Style Transfer[C]//Proceedings of the 25th ACM international conference on Multimedia : 1716–1724

  30. Li Y, Fang C, Yang J, et al. (2017) Universal style transfer via feature transforms [C]//Advances in neural information processing systems : 386–396.

  31. Liu T, Chen ZW, Yang Y, et al. (2020) Lane Detection in Low-light Conditions Using an Efficient Data Enhancement: Light Conditions Style Transfer[C]//Proceedings of the IEEE Intelligent Vehicles Symposium : 1394–1399

  32. Lu M, Zhao H, Yao A, et al. (2017) Decoder network over lightweight reconstructed feature for fast semantic style transfer [C]//Proceedings of the IEEE international conference on computer vision : 2469–2477.

  33. Lu XK, Wang WG, Ma C, et al. (2019) See More, Know More: Unsupervised Video Object Segmentation With Co-Attention Siamese Networks[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition : 3618–3627

  34. Lu XK, Wang WG, Shen JB, Crandall D, Luo J (2020)Zero-shot video object segmentation with co-attention Siamese networks [J]. IEEE Trans Pattern Anal Mach Intell 01:1

    Google Scholar 

  35. Lu XK, Wang WG, Danelljan M, et al. (2020) Video Object Segmentation with Episodic Graph Memory Networks[C]//Proceedings of the European conference on computer vision : 661–679

  36. Lum EB, Ma KL (2001)Non-photorealistic rendering using watercolor inspired textures and illumination[C]//Proceedings Ninth Pacific Conference on Computer Graphics and Applications. Pacific Graphics. IEEE, 2001: 322–330

  37. O’Donovan P and Hertzmann A (2012) Anipaint: Interactive painterly animation from video[J]. IEEE TVCG, 18(3)

  38. Park JH, Park S, Shim H (2019)Semantic-aware neural style transfer[J]. Image Vis Comput 87:13–23

    Article  Google Scholar 

  39. Park SW, Ko JS, Huh JH, Kim JC (2021) Review on generative adversarial networks: focusing on computer vision and its applications [J]. Electronics 10(10):1216

    Article  Google Scholar 

  40. Portilla J, Simoncelli EP (Oct. 2000) A parametric texture model based on joint statistics of complex wavelet coefficients [J]. Int J Comput Vis 40(1):49–70

    Article  Google Scholar 

  41. Qiao YX, Cui JB, Huang FX, Liu H, Bao C, Li X (2021) Efficient style-Corpus constrained learning for photorealistic style transfer[J]. IEEE Trans Image Process 30:3154–3166

    Article  Google Scholar 

  42. Qiao YX, Cui JB, Huang FX, Liu H, Bao C, Li X (2021) Efficient style-Corpus constrained learning for photorealistic style transfer[J]. IEEE Trans Image Process 30:3154–3166

    Article  Google Scholar 

  43. Risser E, Wilmot P, Barnes C (2017) Stable and controllable neural texture synthesis and style transfer using histogram losses[J]. arXiv preprint arXiv:1701.08893

    Google Scholar 

  44. Strothotte T, Schlechtweg S (2002)Non-photorealistic computer graphics: modeling, rendering, and animation[M]. Morgan Kaufmann

    Google Scholar 

  45. Ulyanov D, Vadim Lebedev, Andrea Vedaldi, and Victor S Lempitsky (2016) Texture networks: Feed-forward synthesis of textures and stylized images[M]. In ICML

  46. Ulyanov D, Vedaldi A, Lempitsky V (2016) Instance normalization: The missing ingredient for fast stylization [J]. arXiv preprint arXiv:1607.08022

  47. Wang WJ, Yang S, Xu JZ, Liu J (2020) Consistent video style transfer via relaxation and regularization[J]. IEEE Trans Image Process 29:9125–9139

    Article  Google Scholar 

  48. Wang WJ, Yang S, Xu JZ, Liu J (2020) Consistent video style transfer via relaxation and regularization[J]. IEEE Trans Image Process 29:9125–9139

    Article  Google Scholar 

  49. Wei TT, Zhu LX (2021) Comic style transfer based on generative confrontation network[C]//Proceedings of the 6th International Conference on Intelligent Computing and Signal Processing : 1011–1014

  50. Winnemöller H, Olsen SC, Gooch B (2006)Real-time video abstraction[J]. ACM Transactions On Graphics (TOG) 25(3):1221–1226

    Article  Google Scholar 

  51. Xia XD, Xue TF, Lai WS, et al. (2021)Real-time Localized Photorealistic Video Style Transfer[C]// Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision : 1088–1097

  52. Yao Y, Ren JQ, Xie XS, et al. (2019)Attention-Aware Multi-Stroke Style Transfer[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition : 1467–1475

  53. Ye HM, Liu WJ, Liu YZ (2020) Image Style Transfer Method Based on Improved Style Loss Function[C]//Proceedings of the IEEE 9th Joint International Information Technology and Artificial Intelligence Conference : 410–413

  54. Ye HM, Liu WJ, Liu YZ (2020) Image Style Transfer Method Based on Improved Style Loss Function[C]//Proceedings of the IEEE 9th Joint International Information Technology and Artificial Intelligence Conference : 410–413

  55. Zeng K, Zhao M, Xiong C, et al. (2009) From image parsing to painterly rendering[J]. ACM Trans Graph, 29(1): 2:1–2:11

  56. Zhao C (2020) A Survey on Image Style Transfer Approaches Using Deep Learning[C]. Journal of Physics: Conference Series 1453:012129

    Google Scholar 

  57. Zhao HH, Rosin PL, Lai YK, Wang YN (2020) Automatic semantic style transfer using deep convolutional neural networks and soft masks [J]. Vis Comput 36(7):1307–1324

    Article  Google Scholar 

Download references

Acknowledgements

This work is supported by Key Project of Hebei Provincial Department of Education(ZD2020304).

Author information

Authors and Affiliations

  1. College of Electronics and Information Engineering, Tianjin Key Laboratory of Electronic Materials & Devices, Hebei University of Technology, Tianjin, China

    Wang Yang, Yu Zhenxin & Long Haiyan

Authors
  1. Wang Yang
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Yu Zhenxin
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Long Haiyan
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Wang Yang.

Additional information

Publisher’s note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Yang, W., Zhenxin, Y. & Haiyan, L. Research on style transfer for multiple regions. Multimed Tools Appl 81, 7183–7200 (2022). https://doi.org/10.1007/s11042-022-12121-w

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11042-022-12121-w

Keywords

Search

Navigation