Abstract
We propose a fully automatic approach to restore aged old line drawings. We decompose the task into two subtasks: the line extraction subtask, which aims to extract line fragments and remove the paper texture background, and the restoration subtask, which fills in possible gaps and deterioration of the lines to produce a clean line drawing. Our approach is based on a convolutional neural network that consists of two sub-networks corresponding to the two subtasks. They are trained as part of a single framework in an end-to-end fashion. We also introduce a new dataset consisting of manually annotated sketches by Leonardo da Vinci which, in combination with a synthetic data generation approach, allows training the network to restore deteriorated line drawings. We evaluate our method on challenging 500-year-old sketches and compare with existing approaches with a user study, in which it is found that our approach is preferred 72.7% of the time.
Similar content being viewed by others
References
Barnes, C., Shechtman, E., Finkelstein, A., Goldman, D.B.: PatchMatch: a randomized correspondence algorithm for structural image editing. ACM Trans. Graph. (Proc. of SIGGRAPH 2009) 28(3), 24:1–24:11 (2009)
Bertalmio, M., Sapiro, G., Caselles, V., Ballester, C.: Image inpainting. In: Proceedings of the 27th Annual Conference on Computer Graphics and Interactive Techniques, pp. 417–424 (2000)
Chiang, J.Y., Tue, S., Leu, Y.: A new algorithm for line image vectorization. Pattern Recognit. 31(10), 1541–1549 (1998)
Cugini, U., Ferri, G., Mussio, P., Protti, M.: Pattern-directed restoration and vectorization of digitized engineering drawings. Comput. Graph. 8(4), 337–350 (1984)
Dabov, K., Foi, A., Katkovnik, V., Egiazarian, K.: Image denoising by sparse 3-D transform-domain collaborative filtering. IEEE Trans. Image Process. 16(8), 2080–2095 (2007)
Darabi, S., Shechtman, E., Barnes, C., Goldman, D.B., Sen, P.: Image melding: combining inconsistent images using patch-based synthesis. ACM Trans. Graph. (Proc. SIGGRAPH 2012) 31(4), 82:1–82:10 (2012)
Dong, C., Loy, C.C., He, K., Tang, X.: Learning a deep convolutional network for image super-resolution. In: European Conference on Computer Vision, pp. 184–199. Springer, Berlin (2014)
Favreau, J.D., Lafarge, F., Bousseau, A.: Fidelity vs. simplicity: a global approach to line drawing vectorization. ACM Trans. Graph. (TOG) 35(4), 120 (2016)
Gu, S., Zuo, W., Xie, Q., Meng, D., Feng, X., Zhang, L.: Convolutional sparse coding for image super-resolution. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1823–1831 (2015)
Han, C.C., Fan, K.C.: Skeleton generation of engineering drawings via contour matching. Pattern Recognit. 27(2), 261–275 (1994)
Iizuka, S., Simo-Serra, E., Ishikawa, H.: Globally and locally consistent image completion. ACM Trans. Graph. (Proc. SIGGRAPH 2017) 36(4), 107:1–107:14 (2017)
Ioffe, S., Szegedy, C.: Batch normalization: Accelerating deep network training by reducing internal covariate shift. In: International Conference on Machine Learning (2015)
Jain, V., Seung, S.: Natural image denoising with convolutional networks. In: Advances in Neural Information Processing Systems, pp. 769–776 (2009)
Janssen, R.D., Vossepoel, A.M.: Adaptive vectorization of line drawing images. Comput. Vis. Image Underst. 65(1), 38–56 (1997)
Komodakis, N., Tziritas, G.: Image completion using efficient belief propagation via priority scheduling and dynamic pruning. IEEE Trans. Image Process. 16(11), 2649–2661 (2007)
Li, C., Liu, X., Wong, T.T.: Deep extraction of manga structural lines. ACM Trans. Graph. 36(4), 117:1–117:12 (2017)
Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: Computer Vision and Pattern Recognition, pp. 3431–3440 (2015)
Mao, X., Shen, C., Yang, Y.B.: Image restoration using very deep convolutional encoder–decoder networks with symmetric skip connections. In: Advances in Neural Information Processing Systems, pp. 2802–2810 (2016)
Milanfar, P.: A tour of modern image filtering: new insights and methods, both practical and theoretical. IEEE Signal Process. Mag. 30(1), 106–128 (2013)
Osher, S., Burger, M., Goldfarb, D., Xu, J., Yin, W.: An iterative regularization method for total variation-based image restoration. Multiscale Model. Simul. 4(2), 460–489 (2005)
Pathak, D., Krahenbuhl, P., Donahue, J., Darrell, T., Efros, A.: Context encoders: feature learning by inpainting. In: Computer Vision and Pattern Recognition (2016)
Rudin, L.I., Osher, S., Fatemi, E.: Nonlinear total variation based noise removal algorithms. Phys. D Nonlinear Phenom. 60(1–4), 259–268 (1992)
Sasaki, K., Iizuka, S., Simo-Serra, E., Ishikawa, H.: Joint gap detection and inpainting of line drawings. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)
Simakov, D., Caspi, Y., Shechtman, E., Irani, M.: Summarizing visual data using bidirectional similarity. In: Computer Vision and Pattern Recognition, pp. 1–8 (2008)
Simo-Serra, E., Iizuka, S., Ishikawa, H.: Mastering sketching: adversarial augmentation for structured prediction. Trans. Graph. (TOG) 37(1), 11 (2018)
Simo-Serra, E., Iizuka, S., Sasaki, K., Ishikawa, H.: Learning to simplify: fully convolutional networks for rough sketch cleanup. ACM Trans. Graph. (in Proc. of SIGGRAPH 2016) 35(4), 121 (2016)
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: International Conference on Learning Representations (2015)
Vincent, P., Larochelle, H., Bengio, Y., Manzagol, P.A.: Extracting and composing robust features with denoising autoencoders. In: Proceedings of the 25th International Conference on Machine Learning, pp. 1096–1103. ACM (2008)
Wang, Z., Yang, Y., Wang, Z., Chang, S., Yang, J., Huang, T.S.: Learning super-resolution jointly from external and internal examples. IEEE Trans. Image Process. 24(11), 4359–4371 (2015)
Wexler, Y., Shechtman, E., Irani, M.: Space-time completion of video. IEEE Trans. Pattern Anal. Mach. Intell. 29(3), 463–476 (2007)
Xie, J., Xu, L., Chen, E.: Image denoising and inpainting with deep neural networks. In: Advances in Neural Information Processing Systems, pp. 341–349 (2012)
Zeiler, M.D.: Adadelta: An Adaptive Learning Rate Method. arXiv preprint arXiv:1212.5701 (2012)
Funding
This work was partially supported by JST ACT-I Grant No. JPMJPR16U3, JST ACT-I, Grant No. JPMJPR16UD, and JST CREST Grant No. JPMJCR14D1.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that they have no conflict of interests.
Rights and permissions
About this article
Cite this article
Sasaki, K., Iizuka, S., Simo-Serra, E. et al. Learning to restore deteriorated line drawing. Vis Comput 34, 1077–1085 (2018). https://doi.org/10.1007/s00371-018-1528-4
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00371-018-1528-4