Hallucinating multiple occluded face images of different resolutions

  title={Hallucinating multiple occluded face images of different resolutions},
  author={Kui Jia and Shaogang Gong},
  journal={Pattern Recognition Letters},
Learning-based super-resolution has recently been proposed for enhancing human face images, known as ‘‘face hallucination’’. In this paper, we propose a novel algorithm to super-resolve face images given multiple partially occluded inputs at different lower resolutions. By integrating hierarchical patch-wise alignment and inter-frame constraints into a… CONTINUE READING