Random sampling for fast face sketch synthesis
作者：
Highlights：
• We proposed a simple but effective offline random sampling in place of online K-NN search to improve the efficiency of face sketch synthesis.
• The proposed method could be extended to other heterogeneous face image transformation problems such as face hallucination
• We release the source codes of our proposed methods and the evaluation metrics for future study online: http://www.ihitworld.com/RSLCR.html.
摘要
•We proposed a simple but effective offline random sampling in place of online K-NN search to improve the efficiency of face sketch synthesis.•The proposed method could be extended to other heterogeneous face image transformation problems such as face hallucination•We release the source codes of our proposed methods and the evaluation metrics for future study online: http://www.ihitworld.com/RSLCR.html.
论文关键词：Face sketch synthesis,Locality constraint,Neighbor selection,Random sampling,Weight computation
论文评审过程：Received 11 August 2017, Revised 28 September 2017, Accepted 5 November 2017, Available online 6 November 2017, Version of Record 13 November 2017.
论文官网地址：https://doi.org/10.1016/j.patcog.2017.11.008
