Abstract
Pencil drawing is recognized as a typical non-photorealistic visual art form. It is attractive to automatically generate high-quality pencil drawings from real-world photographs. Traditional model-based methods are highlighted in their interpretability, but are limited in modeling scene semantics, leading to weak sketch lines or limited pencil tone rendering effects. To address this issue, we propose a novel pencil drawing generation method via explicitly leveraging image semantic information. Specifically, the sketch lines generated from the weak boundaries can be boosted by fusing the segmented boundaries. In addition, the segmentation mask provides the spatial guidance for diversifying the tone shading effects. By combining the enhanced pencil drawing patterns, the visual quality of the generated pencil drawings can be therefore strengthened. We conduct several experiments to validate the effectiveness of our method, including ablation studies and comparison with other methods, in which promising results can be obtained.
Similar content being viewed by others
Notes
Meitu Xiu Xiu V8.8.80, Meitu Inc., https://mt.meipai.com
Photo To Sketch - Drawing book V2.8.17, Pexel force private limited
References
Agrawal A (2009) Non-photorealistic rendering: Unleashing the artist’s imagination. IEEE Comput Graph Appl 29(04):81–85
Al-nasrawi M, Deng G, Waheed W (2019) Structure extraction of images using anisotropic diffusion with directional second neighbour derivative operator. Multimed Tools Appl 78(5):6385–6407
Bychkovsky V, Paris S, Chan E, Durand F (2011) Learning photographic global tonal adjustment with a database of input/output image pairs. In: IEEE conference on computer vision and pattern recognition, pp 97–104
Chen LC, Papandreou G, Schroff F, Adam H (2017) Rethinking atrous convolution for semantic image segmentation. arXiv:1706.05587
Chen L, Wu L, Hu Z, Wang M (2019) Quality-aware unpaired image-to-image translation. IEEE Trans Multimed 21(10):2664–2674
Chen Z, Zhou J, Gao X, Li L, Liu J (2008) A novel method for pencil drawing generation in non-photo-realistic rendering. In: Pacific-rim conference on multimedia, pp 931–934
Everingham M, Van Gool L, Williams CK, Winn J, Zisserman A (2010) The pascal visual object classes (voc) challenge. Int J Comput Vis 88 (2):303–338
Ge Q, Wei Z, Liu M, Yu J, Wen C (2020) Adaptive quantized estimation fusion using strong tracking filtering and variational bayesian. IEEE Trans Syst Man Cybern Syst 50(3):899–910
Hao Y, Ngo CW, Huet B (2020d) Neighbourhood structure preserving cross-modal embedding for video hyperlinking. IEEE Trans Multimed 22 (1):188–200
Hao S, Zhou Y, Guo Y (2020a) A brief survey on semantic segmentation with deep learning. Neurocomputing 406:302–321
Hao S, Zhou Y, Guo Y, Hong R (2020b) Bi-direction context propagation network for real-time semantic segmentation. arXiv:2005.11034
Hao S, Zhou Y, Zhang Y, Guo Y (2020c) Contextual attention refinement network for real-time semantic segmentation. IEEE Access 8:55,230–55,240
Inoue N, Ito D, Xu N, Yang J, Price B, Yamasaki T (2019) Learning to trace: Expressive line drawing generation from photographs. Comput Graph Forum 38(7):69–80
Kong Q, Sheng Y, Zhang G (2018) Hybrid noise for lic-based pencil hatching simulation. In: IEEE international conference on multimedia and expo, pp 1–6
Lee H, Kwon S, Lee S (2006) Real-time pencil rendering. In: Proceedings of the international symposium on non-photorealistic animation and rendering, pp 37–45
Li G, Bi S, Wang J, Xu YQ, Yu Y (2017) Colorsketch: A drawing assistant for generating color sketches from photos. IEEE Comput Graph Appl 37(3):70–81
Li Y, Fang C, Hertzmann A, Shechtman E, Yang MH (2019b) Im2pencil: Controllable pencil illustration from photographs. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1525–1534
Li X, Li X, Zhang L, Cheng G, Shi J, Lin Z, Tan S, Tong Y (2020) Improving semantic segmentation via decoupled body and edge supervision. arXiv:2007.10035
Li H, Xiong P, Fan H, Sun J (2019a) Dfanet: Deep feature aggregation for real-time semantic segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 9522–9531
Lin TY, Maire M, Belongie S, Hays J, Perona P, Ramanan D, Dollár P, Zitnick CL (2014) Microsoft coco: Common objects in context. In: Fleet D, Pajdla T, Schiele B, Tuytelaars T (eds) European conference on computer vision, pp 740–755
Long J, Shelhamer E, Darrell T (2015) Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3431–3440
Lu P, Sheng B, Luo S, Jia X, Wu W (2015) Image-based non-photorealistic rendering for realtime virtual sculpting. Multimed Tools Appl 74(21):9697–9714
Lu C, Xu L, Jia J (2012) Combining sketch and tone for pencil drawing production. In: Proceedings of the symposium on non-photorealistic animation and rendering, pp 65–73
Mao X, Nagasaka Y, Imamiya A (2002) Automatic generation of pencil drawing using lic. In: ACM SIGGRAPH 2002 conference abstracts and applications, p 149
Mukundan R (2015) Multi-level stroke textures for sketch based non-photorealistic rendering. In: International conference and workshop on computing and communication, pp 1–7
Paszke A, Chaurasia A, Kim S, Culurciello E (2016) Enet: A deep neural network architecture for real-time semantic segmentation. arXiv:1606.02147
Qiu J, Liu B, He J, Liu C, Li Y (2019) Parallel fast pencil drawing generation algorithm based on gpu. IEEE Access 7:83,543–83,555
Ronneberger O, Fischer P, Brox T (2015) U-net: Convolutional networks for biomedical image segmentation. In: International conference on medical image computing and computer-assisted intervention, pp 234–241
Rother C, Kolmogorov V, Blake A (2004) “rabcut”: Interactive foreground extraction using iterated graph cuts. ACM Trans Graph 23(3):309–314
Sandler M, Howard A, Zhu M, Zhmoginov A, Chen LC (2018) Mobilenetv2: Inverted residuals and linear bottlenecks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4510–4520
Son M, Kang H, Lee Y, Lee S (2007) Abstract line drawings from 2d images. In: Pacific conference on computer graphics and applications, pp 333–342
Winnemöller H (2011) Xdog: advanced image stylization with extended difference-of-gaussians. In: Proceedings of the ACM SIGGRAPH/eurographics symposium on non-photorealistic animation and rendering, pp 147–156
Xie J, Bian H, Wu Y, Zhao Y, Shan L, Hao S (2020) Semantically-guided low-light image enhancement. Pattern Recogn Lett 138:308–314
Yan D, Sheng Y, Mao X (2019) Pencil drawing video rendering using convolutional networks. Comput Graph Forum 38(7):91–102
Yeh JW, Ouhyoung M (2009) Non-photorealistic rendering in chinese painting of animals. J Syst Simul 14:1220–1224. 1262
Yu J, Huang D, Wei Z (2018) Unsupervised image segmentation via stacked denoising auto-encoder and hierarchical patch indexing. Signal Process 143:346–353
Zhao H, Shi J, Qi X, Wang X, Jia J (2017) Pyramid scene parsing network. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2881–2890
Zheng Y, Chen Y, Sarem M (2019) A novel pencil drawing algorithm based on non-symmetry and anti-packing pattern representation model. IEEE Access 7:184,950–184,962
Acknowledgment
The research was supported by the National Undergraduate Innovation and En-trepreneurship Training Program with Grant No. 202010359089.
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Li, T., Xie, J., Niu, H. et al. Enhancing pencil drawing patterns via using semantic information. Multimed Tools Appl 81, 34245–34262 (2022). https://doi.org/10.1007/s11042-021-11028-2
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-021-11028-2