Face hallucination from low quality images using definition-scalable inference
作者：
Highlights：
• A method is introduced to hallucinate super-low face from real low-quality face instead of stimulated low-quality face.
• A definition-scalable strategy: a face is decomposed into a basic face with low-definition and an enhanced face with high-frequency information.
• The super-resolution technique based on definition-scalable inference effectively estimate structural information and high-frequency texture from real low-res faces.
• The matched SIFT key-points is proposed to estimate the similarity of the super-res face and its high-res labeled face.
• The proposed SISR method can recover more structure information and local information from real low-quality face and more SIFT key-points than the state of the arts.
摘要
•A method is introduced to hallucinate super-low face from real low-quality face instead of stimulated low-quality face.•A definition-scalable strategy: a face is decomposed into a basic face with low-definition and an enhanced face with high-frequency information.•The super-resolution technique based on definition-scalable inference effectively estimate structural information and high-frequency texture from real low-res faces.•The matched SIFT key-points is proposed to estimate the similarity of the super-res face and its high-res labeled face.•The proposed SISR method can recover more structure information and local information from real low-quality face and more SIFT key-points than the state of the arts.
论文关键词：SIFT,PCA,Sparse representation,Deep learning,Generative adversarial networks
论文评审过程：Received 16 July 2018, Revised 18 April 2019, Accepted 15 May 2019, Available online 16 May 2019, Version of Record 27 May 2019.
论文官网地址：https://doi.org/10.1016/j.patcog.2019.05.027
