Zhenli Wei

  • Citations Per Year
Learn More
In most of the existing LLE (Local Linear Embedding) based face hallucination methods, a LR (Low Resolution) face image is usually represented as a linear combination of training samples. The combination coefficients of LR image are then directly used to estimate the HR (High Resolution) image. However, due to the one-to-many mapping from LR to HR face(More)
  • 1