Semi-Supervised Learning for Face Sketch Synthesis in the Wild

12 Dec 2018Chaofeng ChenWei LiuXiao TanKwan-Yee K. Wong

Face sketch synthesis has made great progress in the past few years. Recent methods based on deep neural networks are able to generate high quality sketches from face photos... (read more)

PDF Abstract

Evaluation results from the paper


Task Dataset Model Metric name Metric value Global rank Compare
Face Sketch Synthesis CUFS Residual net + Pseudo Sketch Feature Loss + LSGAN FSIM 72.56% # 1
Face Sketch Synthesis CUFS Residual net + Pseudo Sketch Feature Loss + LSGAN SSIM 54.63% # 1
Face Sketch Synthesis CUFSF Residual net + Pseudo Sketch Feature Loss + LSGAN FSIM 71.59% # 1
Face Sketch Synthesis CUFSF Residual net + Pseudo Sketch Feature Loss + LSGAN SSIM 40.85% # 1
Face Sketch Synthesis CUHK Residual net + Pseudo Sketch Feature Loss + LSGAN SSIM 63.28% # 1
Face Sketch Synthesis CUHK Residual net + Pseudo Sketch Feature Loss + LSGAN FSIM 74.23% # 1