eduzhai > Applied Sciences > Engineering >

Image De-Quantization Using Generative Models as Priors

  • king
  • (0) Download
  • 20210506
  • Save

... pages left unread,continue reading

Document pages: 7 pages

Abstract: Image quantization is used in several applications aiming in reducing thenumber of available colors in an image and therefore its size. De-quantizationis the task of reversing the quantization effect and recovering the originalmulti-chromatic level image. Existing techniques achieve de-quantization byimposing suitable constraints on the ideal image in order to make the recoveryproblem feasible since it is otherwise ill-posed. Our goal in this work is todevelop a de-quantization mechanism through a rigorous mathematical analysiswhich is based on the classical statistical estimation theory. In this effortwe incorporate generative modeling of the ideal image as a suitable priorinformation. The resulting technique is simple and capable of de-quantizingsuccessfully images that have experienced severe quantization effects.Interestingly, our method can recover images even if the quantization processis not exactly known and contains unknown parameters.

Please select stars to rate!

         

0 comments Sign in to leave a comment.

    Data loading, please wait...
×