Scene Completion Using Millions of Photographs
Computer Graphics in 2-Dimensions

 

Project Description:
 

What can you do with million images? In this project a new image completion algorithm powered by a huge database of photographs gathered from the Web will be implemented. The algorithm patches up holes in images by finding similar image regions in the database that are not only seamless but also semantically valid.

Reference: Scene Completion Using Millions of Photographs



Project Goal:
 

In this project we will implement the article written by James Hays et al. and try to improve it in its weakness points.

Project Details:
 
  1. Supervisor:
    Gur Harary
    Phone: 04-8295741/4630
    Email: gur@tx.technion.ac.il
  2. Field:
    Computer Graphics in 2-Dimensions
  3. Requirements:
    Good programming skills, open minds...
  4. Project status:
    Taken by the students Or Cohen and Alona Zadneprovski
  5. Visit:
    Project web site
 
Current Projects Archive
CG&M Lab    Contact Us EE Labs EE Department Technion