Image Super-Resolution using Gradient Profile Prior
Computer Graphics and Modern Art


Project Description:

Super resolution is one of the most important tasks in computer vision and computer graphics. We will implement a super-resolution approach using a novel generic image prior – gradient profile prior, which is a parametric prior describing the shape and the sharpness of the image gradients. Using the gradient profile prior learned from a large number of natural images, we can provide a constraint on image gradients when we estimate a hi-resolution image from a low-resolution image. With this simple but very effective prior, we are able to produce state-of-the-art results. The reconstructed high-resolution image is sharp while has rare ringing or jaggy artifacts.

Project Goal:

In this project we will develop algorithm and create an application.

Project Details:
  1. Supervisor:
    Michael Kolomenkin
    Phone: 04-8295741
  2. Field:
    Computer Graphics and Modern Art
  3. Requirements:
    MATLAB or C/C++
    Computer Graphics or Image Processing

  4. Project status:
  5. Project status:
    Taken by the students Liran Sperling and Roi Rahin
    Project web site
Current Projects Archive
CG&M Lab    Contact Us EE Labs ECE Department Technion