Skip to main content
SpringerLink
Log in

Iterative unsupervised deep bilateral texture filtering

  • Original article
  • Published:
The Visual Computer Aims and scope Submit manuscript

Abstract

Texture filtering attempts to retain salient structures and remove insignificant textures. In this paper, we propose a highly effective iterative unsupervised deep bilateral texture filtering neural network for texture smoothing. The bilateral texture loss function is introduced to train the model without the ground truth smoothing images for guidance. The proposed model inherits well-known advantages of the bilateral texture filter to capture the texture information effectively. The model is trained solely using the training data, then the predicted outputs are generated iteratively through multiple forward passes. Extensive experiments demonstrate that our proposed iterative unsupervised deep bilateral texture filtering neural network outperforms existing methods in effectively removing textures while preserving the main structures of the image. The results showcase the superior performance of our approach and its ability to achieve high-quality texture smoothing without sacrificing important image features.

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

Access this article

Log in via an institution

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

Similar content being viewed by others

References

  1. Zhu, F., Liang, Z., Jia, X., Zhang, L., Yizhou, Yu.: A benchmark for edge-preserving image smoothing. IEEE Trans. Image Process. 28(7), 3556–3570 (2019)

    Article  MathSciNet  Google Scholar 

  2. Liu, W., Zhang, P., Huang, X., Yang, J., Shen, C., Reid, I.: Real-time image smoothing via iterative least squares. ACM Trans. Graph. (TOG) 39(3), 1–24 (2020)

    Article  Google Scholar 

  3. Li, Y., Huang, J.-B., Ahuja, N., Yang, M.-H.: Joint image filtering with deep convolutional networks. IEEE Trans. Pattern Anal. Mach. Intell. 41(8), 1909–1923 (2019)

    Article  Google Scholar 

  4. Liu, W., Zhang, P., Lei, Y., Huang, X., Yang, J., Ng, M.: A generalized framework for edge-preserving and structure-preserving image smoothing. IEEE Trans. Pattern Anal. Mach. Intell. 44, 6631–6648 (2021)

    Article  Google Scholar 

  5. Cho, H., Lee, H., Kang, H., Lee, S.: Bilateral texture filtering. ACM Trans. Graph. (TOG) 33(4), 1–8 (2014)

    Article  Google Scholar 

  6. Ruhela, R., Gupta, B., Lamba, S.: An efficient approach for texture smoothing by adaptive joint bilateral filtering. Vis. Comput. 39, 2035–2049 (2022)

    Article  Google Scholar 

  7. Song, C., Xiao, C., Li, X., Li, J., Sui, H.: Structure-preserving texture filtering for adaptive image smoothing. J. Vis. Lang. Comput. 45, 17–23 (2018)

    Article  Google Scholar 

  8. Jeon, J., Lee, H., Kang, H., Lee, S.: Scale-aware structure-preserving texture filtering. Comput. Graph. Forum 35, 77–86 (2016)

    Article  Google Scholar 

  9. Lin, T.-H., Way, D.-L., Shih, Z.-C., Tai, W.-K., Chang, C.-C.: An efficient structure-aware bilateral texture filtering for image smoothing. Comput. Graph. Forum 35, 57–66 (2016)

    Article  Google Scholar 

  10. Zhang, Q., Shen, X., Xu, L., Jia, J.: Rolling guidance filter. In: European Conference on Computer Vision, pp. 815–830. Springer (2014)

  11. Zhou, P.-C., Xue, Y., Xue, M.-G.: Adaptive side window joint bilateral filter. Vis. Comput. 39, 1533–1555 (2022)

    Google Scholar 

  12. Panpan, X., Wang, W.: Improved bilateral texture filtering with edge-aware measurement. IEEE Trans. Image Process. 27(7), 3621–3630 (2018)

    Article  MathSciNet  Google Scholar 

  13. Gavaskar, R.G., Chaudhury, K.N.: Fast adaptive bilateral filtering. IEEE Trans. Image Process. 28(2), 779–790 (2018)

    Article  MathSciNet  Google Scholar 

  14. Zhao, H., Jiang, L., Jin, X., Hui, D., Li, X.: Constant time texture filtering. Vis. Comput. 34(1), 83–92 (2018)

    Article  Google Scholar 

  15. Gupta, B., Lamba, S.S., et al.: Structure-aware adaptive bilateral texture filtering. Digit. Signal Process. 123, 103386 (2022)

    Article  Google Scholar 

  16. He, K., Sun, J., Tang, X.: Guided image filtering. IEEE Trans. Pattern Anal. Mach. Intell. 35(6), 1397–1409 (2012)

    Article  Google Scholar 

  17. Zhang, F., Dai, L., Xiang, S., Zhang, X.: Segment graph based image filtering: fast structure-preserving smoothing. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 361–369 (2015)

  18. Li, X., Yan, Q., Xia, Y., Jia, J.: Structure extraction from texture via relative total variation. ACM Trans. Graph. (TOG) 31(6), 1–10 (2012)

    Article  Google Scholar 

  19. Liu, Q., Xiong, B., Yang, D., Zhang, M.: A generalized relative total variation method for image smoothing. Multimed. Tools Appl. 75(13), 7909–7930 (2016)

    Article  Google Scholar 

  20. Min, D., Choi, S., Lu, J., Ham, B., Sohn, K., Do, M.N.: Fast global image smoothing based on weighted least squares. IEEE Trans. Image Process. 23(12), 5638–5653 (2014)

    Article  MathSciNet  Google Scholar 

  21. Liu, W., Chen, X., Shen, C., Liu, Z., Yang, J.: Semi-global weighted least squares in image filtering. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 5861–5869 (2017)

  22. Farbman, Z., Fattal, R., Lischinski, D., Szeliski, R.: Edge-preserving decompositions for multi-scale tone and detail manipulation. ACM Trans. Graph. (TOG) 27(3), 1–10 (2008)

    Article  Google Scholar 

  23. Xu, L., Lu, C., Xu, Y., Jia, J.: Image smoothing via L0 gradient minimization. In: Proceedings of the 2011 SIGGRAPH Asia Conference, pp. 1–12 (2011)

  24. Zhang, Z., He, H.: A customized low-rank prior model for structured cartoon-texture image decomposition. Signal Process. Image Commun. 96, 116308 (2021)

    Article  Google Scholar 

  25. Xu, L., Ren, J., Yan, Q., Liao, R., Jia, J.: Deep edge-aware filters. In: International Conference on Machine Learning, pp. 1669–1678. PMLR (2015)

  26. Li, Y., Huang, J.-B., Ahuja, N., Yang, M.-H.: Deep joint image filtering. In: European Conference on Computer Vision, pp. 154–169. Springer (2016)

  27. Fan, Q., Dongdong Chen, L., Yuan, G.H., Nenghai, Yu., Chen, B.: A general decoupled learning framework for parameterized image operators. IEEE Trans. Pattern Anal. Mach. Intell. 43(1), 33–47 (2019)

    Article  Google Scholar 

  28. Lu, K., You, S., Barnes, N.: Deep texture and structure aware filtering network for image smoothing. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 217–233 (2018)

  29. Zhu, D., Wang, W., Xue, X., Xie, H., Cheng, G., Wang, F.L.: Structure-preserving image smoothing via contrastive learning. Vis. Comput. (2023)

  30. Fang, X., Wang, M., Shamir, A., Hu, S.-M.: Learning explicit smoothing kernels for joint image filtering. Comput. Graph. Forum 38, 181–190 (2019)

    Article  Google Scholar 

  31. Jun, X., Liu, Z.-A., Hou, Y.-K., Zhen, X.-T., Shao, L., Cheng, M.-M.: Pixel-level non-local image smoothing with objective evaluation. IEEE Trans. Multimed. 23, 4065–4078 (2020)

    Google Scholar 

  32. Fan, Q., Yang, J., Wipf, D., Chen, B., Tong, X.: Image smoothing via unsupervised learning. ACM Trans. Graph. (TOG) 37(6), 1–14 (2018)

    Article  Google Scholar 

  33. Zhou, F., Chen, Q., Liu, B., Qiu, G.: Structure and texture-aware image decomposition via training a neural network. IEEE Trans. Image Process. 29, 3458–3473 (2019)

    Article  Google Scholar 

  34. Wang, C., Xu, L., Liu, L.: Structure–texture image decomposition via non-convex total generalized variation and convolutional sparse coding. Vis. Comput. 1–16 (2022)

  35. Yu, F., Koltun, V., Funkhouser, T.: Dilated residual networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition 472–480 (2017)

  36. Paszke, A., Gross, S., Massa, F., Lerer, A., Bradbury, J., Chanan, G., Killeen, T., Lin, Z., Gimelshein, N., Antiga, L., et al.: Pytorch: an imperative style, high-performance deep learning library. Adv. Neural Inf. Process. Syst. 32 (2019)

  37. Avidan, S., Shamir, A.: Seam carving for content-aware image resizing. ACM Trans. Graph. 26(3), 10 (2007)

    Article  Google Scholar 

Download references

Acknowledgements

This work was supported by the Zhejiang Provincial Natural Science Foundation of China (Grant Nos. LY18 F020022 and LQ17F020002).

Author information

Authors and Affiliations

  1. Zhejiang College of Security Technology, Wenzhou, 325016, China

    Lixi Jiang

  2. Intelligent Information Systems Institute, Wenzhou University, Wenzhou, 325035, China

    Xujie Li & Yandan Wang

Authors
  1. Lixi Jiang
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Xujie Li
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Yandan Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Lixi Jiang.

Ethics declarations

Conflict of interest

The authors declare that they have no conflict of interest.

Additional information

Publisher's Note

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

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Jiang, L., Li, X. & Wang, Y. Iterative unsupervised deep bilateral texture filtering. Vis Comput 40, 3055–3067 (2024). https://doi.org/10.1007/s00371-023-03010-w

Download citation

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00371-023-03010-w

Keywords

Search

Navigation