Skip to main content
SpringerLink
Log in

Unsupervised bas-relief generation with feature transferring

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

Abstract

The generation of relief based on 3D models has always been a research hotspot in computer graphics. The challenge of bas-relief generation lies in the need to maintain details and eliminate height jumps while significantly compressing height. Traditional algorithms are computationally complex. The latest methods based on deep learning bring new ideas to the problem but are rely on supervised training, which requires a large number of samples to be constructed manually. In this paper, an unsupervised bas relief generation method is proposed. In the method, the normal image of the model is modified by a style-transfer neural network firstly, and then it is reconstructed by Convolution Neural Network (CNN). Our method takes the orthogonal relationship between the normal vector and the local points as the optimization goal, thus avoiding the process of constructing “ground truth”. At the same time, by adding normal vector continuity constraints to the style-transfer network and the reconstruction network, the high jump in the original model is effectively eliminated, and the detailed features are well maintained. Experiments show that this method is simple and efficient, and can generate a series of pleasant stylized relief models with rich details and good saturation.

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
Fig. 13
Fig. 14
Fig. 15

Similar content being viewed by others

Data availability

The datasets generated or analyzed during the current study are available from the corresponding author on reasonable request.

References

  1. Alexa M, Matusik W (2010) Reliefs Images ACM Trans Graph 29(4):60–61

    Google Scholar 

  2. Belhumeur PN, Kriegman D-J, Yuille A-L (1999) The bas-relief ambiguity. Int J Comput Vis 35(1):33–44

    Article  Google Scholar 

  3. Cignoni P, Montani C, Scopigno R (1997) Computer-assisted generation of bas-and high-reliefs. J Graph Tools 2:15–28

    Article  Google Scholar 

  4. Fattal R, Lischinski D, Werman M (2002) Gradient domain high dynamic range compression. ACM Trans Graph 21(3):249–256

    Article  Google Scholar 

  5. Galna B, Barry G, Jackson D et al (2014) Accuracy of the Microsoft Kinect sensor for measuring movement in people with Parkinson's disease. Gait Posture 39(4):1062–1068

    Article  Google Scholar 

  6. Hssayni, EH, Joudar, NE, Ettaouil M (2022) KRR-CNN: kernels redundancy reduction in convolutional neural networks. Neural Comput & Applic 34:2443–2454

  7. Ji Z, Ma W, Sun X (2013) Bas-relief modeling from normal images with intuitive styles. IEEE Trans Vis Comput Graph 20(5):675–685

    Article  Google Scholar 

  8. Ji Z, Feng W, Sun X et al (2021) ReliefNet: fast bas-relief generation from 3D scenes. Comput Aided Des 130:102928

    Article  MathSciNet  Google Scholar 

  9. Junior FEF, Yen GG (2019) Particle swarm optimization of deep neural networks architectures for image classification. Swarm Evol Comput 49:62–74

    Article  Google Scholar 

  10. Kerber J, Belyaev A, Seidel H-P (2007) Feature preserving depth compression of range images. Proceedings of the 23rd spring conference on computer graphics. ACM p 101–105

  11. Kerber J, Tevs A, Belyaev A, Zayer R, Seidel H-P (2009) Feature sensitive bas relief generation. In: Shapemodeling and applications, 2009. SMI 2009. IEEE international conference on. IEEE, p 148–154

  12. Kerber J, Wang M, Chang J et al (2012) Computer assisted relief generation-a survey. Comput Graph Forum 31(8):2363–2377

    Article  Google Scholar 

  13. Khoshelham K, Elberink SO (2012) Accuracy and resolution of kinect depth data for indoor mapping applications. Sensors 12(2):1437–1454

    Article  Google Scholar 

  14. Lee C-H, Varshney A, Jacobs D-W (2005) Mesh Saliency ACM Trans Graph 24(3):659–666

    Article  Google Scholar 

  15. Li B, Liu S-L, Zhang L-Y et al (2011) Bas-relief generation algorithm based on Laplace operator decomposition of 3d model. Comput Integr Manuf Syst 17(5):946–951

    Google Scholar 

  16. Nie J, Shi W, Liu Y et al (2021) Bas-relief generation from point clouds based on normal space compression with real-time adjustment on CPU. Graph Model 113:101096

    Article  Google Scholar 

  17. Schüller C, Panozzo D, Sorkine-Hornung O (2014) Appearance-Mimicking Surfaces ACM Trans Graph 36(6):1–10

    Google Scholar 

  18. Song W, Belyaev A, Seidel H-P (2007) Automatic generation of bas-reliefs from 3d shapes. In: Shape modeling and applications, 2007. SMI’07. IEEE international conference on. IEEE, p 211–214

  19. Sun X, Rosin PL, Martin RR, Langbein FC (2009) Bas-relief generation using adaptive histogram equalization. IEEE Trans Vis Comput Graph 15:642–653

    Article  Google Scholar 

  20. Sýkora D, Kavan L, Čadík M et al (2014) Ink-and-ray: bas-relief meshes for adding global illumination effects to hand-drawn characters. ACM Trans Graph 33(2):1–15

    Article  Google Scholar 

  21. Wei M, Tian Y, Pang WM (2018) Bas-relief modeling from normal layers. IEEE Trans Vis Comput Graph 25(4):1651–1665

    Article  Google Scholar 

  22. Weyrich DJ, Barnes C, Rusinkiewicz S, Finkelstein A (2007) Digital bas-relief from 3d scenes. ACM Trans Graph 26(3):32

    Article  Google Scholar 

  23. Yang Z, Chen B, Zheng Y et al (2021) Human bas-relief generation from a single photograph. EEE Trans Vis Comput Graph 28(12):4558–4569

    Article  Google Scholar 

  24. Yang Y, Zhuang Y, Pan Y (2021) Multiple knowledge representation for big data artificial intelligence: framework, applications, and case studies. Front Inf Technol Electron Eng 22(12):1551–1558

    Article  Google Scholar 

  25. Zhang Y-W, Zhou Y-Q, Zhao X-F, Yu G (2013) Real-time bas-relief generation from a 3d mesh. Graph Model 75(1):2–9

    Article  Google Scholar 

  26. Zhang Y-W, Zhou Y-Q, Li X-L et al (2014) Bas-relief generation and shape editing through gradient-based mesh deformation. IEEE Trans Vis Comp Graph 21(3):328–338

    Article  Google Scholar 

  27. Zhang Y-W, Zhang C, Wang W, Chen Y (2016) Adaptive bas-relief generation from 3d object under illumination. Comput Graph Forum 35(7):311–321

    Article  Google Scholar 

  28. Zhang YW, Zhang C, Wang W et al (2019) Portrait relief modeling from a single image. IEEE Trans Vis Comput Graph 26(8):2659–2670

    Article  Google Scholar 

  29. Zhang Y-W, Wang J, Long W et al (2020) A fast solution for Chinese calligraphy relief modeling from 2d handwriting image. Vis Comput 36(10):2241–2250

    Article  Google Scholar 

  30. Zhang Y-W, Wang J, Wang W et al (2021) Neural modelling of flower bas-relief from 2D line drawing. Com Comput Graph Forum 40(6):288–303

    Article  Google Scholar 

  31. Zhang Y-W, Luo P, Zhou H et al (2022) Neural modeling of portrait bas-relief from a single photograph. IEEE Trans Vis Comput Graph

Download references

Acknowledgements

We would like to thank all the reviewers for their valuable comments. This work is supported by NSFC (No. 61802204).

Author information

Authors and Affiliations

  1. School of Automation & Artificial Intelligence, Nanjing University of Posts and Telecommunications, Nanjing, China

    Xiao Liu & Jianhui Nie

Authors
  1. Xiao Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Jianhui Nie
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Jianhui Nie.

Ethics declarations

Conflict of interests

The authors declare that they have no conflicts 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

Liu, X., Nie, J. Unsupervised bas-relief generation with feature transferring. Multimed Tools Appl 83, 13181–13195 (2024). https://doi.org/10.1007/s11042-023-16111-4

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11042-023-16111-4

Keywords

Search

Navigation