Hallucinating Face in the DCT Domain

Wei Zhang, Wai-Kuen Cham

  • Left: One frame (320*240) of the surveillance video captured by a web camera.
  • Right: The input face (top) and the hallucinated face (bottom).


In this work, we propose a novel learning-based face hallucination framework built in the DCT domain, which can produce a high-resolution face image from a single low-resolution one. The problem is formulated as inferring the DCT coefficients in frequency domain instead of estimating pixel intensities in spatial domain. Our study shows that DC coefficients can be estimated fairly accurately by simple interpolation-based methods. AC coefficients, which contain the information of local features of face image, cannot be estimated well using interpolation. A simple but effective learning-based inference model is proposed to infer the AC coefficients. Experiments have been conducted to demonstrate the effectiveness of the proposed method in producing high quality hallucinated face images.


  1. Wei Zhang and Wai-Kuen Cham. Learning-based Face Hallucination in DCT Domain. Proc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Alaska, USA, Jun. 2008.
  2. Wei Zhang and Wai-Kuen Cham. Hallucinating Face in the DCT Domain. IEEE Transactions on Image Processing (T-IP). Vol.20, Oct. 2011.

Supplementary Results

Positive Results:

Negative Results:

Notes:In each triple,
  • Left: The input LRI (24*32);
  • Middle: the hallucinated result by the proposed method;
  • Right: the original HRI (96*128).

Back to Home