Improving Image Restoration with Soft-Rounding

  title={Improving Image Restoration with Soft-Rounding},
  author={X. Mei and H. Qi and B. Hu and Siwei Lyu},
  journal={2015 IEEE International Conference on Computer Vision (ICCV)},
  • X. Mei, H. Qi, +1 author Siwei Lyu
  • Published 2015
  • Computer Science, Mathematics
  • 2015 IEEE International Conference on Computer Vision (ICCV)
Several important classes of images such as text, barcode and pattern images have the property that pixels can only take a distinct subset of values. This knowledge can benefit the restoration of such images, but it has not been widely considered in current restoration methods. In this work, we describe an effective and efficient approach to incorporate the knowledge of distinct pixel values of the pristine images into the general regularized least squares restoration framework. We introduce a… Expand
5 Citations
Text image deblurring via two-tone prior
  • 20
Image Correction via Deep Reciprocating HDR Transformation
  • 42
  • PDF
Binary image deblurring with automatic binary value estimation
  • 1
ℓp-Box ADMM: A Versatile Framework for Integer Programming
  • 32
  • PDF


Shrinkage Fields for Effective Image Restoration
  • Uwe Schmidt, S. Roth
  • Computer Science
  • 2014 IEEE Conference on Computer Vision and Pattern Recognition
  • 2014
  • 362
  • PDF
UniHIST: A unified framework for image restoration with marginal histogram constraints
  • 9
  • PDF
Digital image restoration
  • 661
A content-aware image prior
  • 99
  • PDF
Image deblurring and denoising using color priors
  • 86
  • PDF
Nonlinear Image Recovery with
  • 50
  • Highly Influential
Deblurring Text Images via L0-Regularized Intensity and Gradient Prior
  • 280
  • Highly Influential
  • PDF
Image smoothing via L0 gradient minimization
  • 848
  • PDF
Image quality assessment: from error visibility to structural similarity
  • 25,899
  • Highly Influential
  • PDF
Gradient Histogram Estimation and Preservation for Texture Enhanced Image Denoising
  • 98
  • PDF