SCIENCE CHINA Information Sciences, Volume 63 , Issue 11 : 219103(2020) https://doi.org/10.1007/s11432-019-2890-8

Face-sketch learning with human sketch-drawing order enforcement

More info
  • ReceivedNov 27, 2019
  • AcceptedFeb 26, 2020
  • PublishedOct 12, 2020


There is no abstract available for this article.


This work was supported by National Key RD Program of China (Grant Nos. 2017YFB1402105, 2019YFC1521100), National Natural Science Foundation of China (Grant Nos. U1805264, 61573359, 61672103, 61473276, 61402040), and Natural Science Foundation of Beijing (Grant No. L182052).


Appendixes A–C.


[1] Xiaogang Wang , Xiaoou Tang . Face Photo-Sketch Synthesis and Recognition. IEEE Trans Pattern Anal Mach Intell, 2009, 31: 1955-1967 CrossRef Google Scholar

[2] Zhang M, Wang N, Li Y. Neural Probabilistic Graphical Model for Face Sketch Synthesis. IEEE Trans Neural Netw Learning Syst, 2019, : 1-15 CrossRef Google Scholar

[3] Wang N, Gao X, Sun L. Anchored Neighborhood Index for Face Sketch Synthesis. IEEE Trans Circuits Syst Video Technol, 2018, 28: 2154-2163 CrossRef Google Scholar

[4] Deep Supervised, but Not Unsupervised, Models May Explain IT Cortical Representation. PLoS Comput Biol, 2014, 10: e1003915 CrossRef ADS Google Scholar

[5] Goodfellow I J, Pouget-Abadie J, Mirza M, et al. Generative adversarial nets. In: Proceedings of Annual Conference on Neural Information Processing Systems (NIPS), 2014. 2672--2680. Google Scholar

[6] Isola P, Zhu J, Zhou T, et al. Image-to-image translation with conditional adversarial networks. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017. 5967--5976. Google Scholar

[7] Ronneberger O, Fischer P, Brox T. U-net: convolutional networks for biomedical image segmentation. In: Proceedings of International Conference on Medical Image Computing and Computer-assisted Intervention, 2015. 234--241. Google Scholar

[8] Zhang W, Wang X, Tang X. Coupled information-theoretic encoding for face photo-sketch recognition. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2011. 513--520. Google Scholar

  • Figure 1

    (Color online) (a) An example sequence of 25 sketches for a given photo in the Ord-Sketch dataset. The five key sketches selected for training are highlighted with blue rectangles. (b) The architecture of SO-Net, which is a five-stage cGAN model with photos as input.