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.
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
Alexa M, Matusik W (2010) Reliefs Images ACM Trans Graph 29(4):60–61
Belhumeur PN, Kriegman D-J, Yuille A-L (1999) The bas-relief ambiguity. Int J Comput Vis 35(1):33–44
Cignoni P, Montani C, Scopigno R (1997) Computer-assisted generation of bas-and high-reliefs. J Graph Tools 2:15–28
Fattal R, Lischinski D, Werman M (2002) Gradient domain high dynamic range compression. ACM Trans Graph 21(3):249–256
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
Hssayni, EH, Joudar, NE, Ettaouil M (2022) KRR-CNN: kernels redundancy reduction in convolutional neural networks. Neural Comput & Applic 34:2443–2454
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
Ji Z, Feng W, Sun X et al (2021) ReliefNet: fast bas-relief generation from 3D scenes. Comput Aided Des 130:102928
Junior FEF, Yen GG (2019) Particle swarm optimization of deep neural networks architectures for image classification. Swarm Evol Comput 49:62–74
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
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
Kerber J, Wang M, Chang J et al (2012) Computer assisted relief generation-a survey. Comput Graph Forum 31(8):2363–2377
Khoshelham K, Elberink SO (2012) Accuracy and resolution of kinect depth data for indoor mapping applications. Sensors 12(2):1437–1454
Lee C-H, Varshney A, Jacobs D-W (2005) Mesh Saliency ACM Trans Graph 24(3):659–666
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
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
Schüller C, Panozzo D, Sorkine-Hornung O (2014) Appearance-Mimicking Surfaces ACM Trans Graph 36(6):1–10
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
Sun X, Rosin PL, Martin RR, Langbein FC (2009) Bas-relief generation using adaptive histogram equalization. IEEE Trans Vis Comput Graph 15:642–653
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
Wei M, Tian Y, Pang WM (2018) Bas-relief modeling from normal layers. IEEE Trans Vis Comput Graph 25(4):1651–1665
Weyrich DJ, Barnes C, Rusinkiewicz S, Finkelstein A (2007) Digital bas-relief from 3d scenes. ACM Trans Graph 26(3):32
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
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
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
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
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
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
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
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
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
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
Corresponding author
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.
About this article
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
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-023-16111-4