Chen Chen — Publications

J. Jiang, Z. Wang, C. Chen, and T. Lu, “L1-L1 Norms for Face Super-Resolution with Mixed Gaussian-Impulse Noise,” the 41st IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Shanghai, China, March 2016, accepted.
  • Abstract:
    In real world surveillance application, the captured faces are often low resolution (LR) and corrupted by mixed Gaussianimpulse noise during the acquisition and transmission processes. In this paper, we propose an effective patch-based face super-resolution method to reconstruct a high resolution (HR) face image given an LR observation that is corrupted by mixed Gaussian-impulse noise. To represent the corrupted image patches, a sparse regularization combined with an l1 data fitting term is proposed. In the proposed model, both the patch reconstruction term and the regularization term are in the l1 norm form. As a result, the model is called l1-l1 norms. In addition, since image pixels have nonnegative intensities, we further add a nonnegative constraint to the patch representation model. Experimental results demonstrate that the proposed l1-l1 norms based method can achieve superior face super-resolution performance over several state-of-theart approaches based on the objective results in terms of PSNR, as well as the visual perceptual quality.

  • [PDF]