Removing Photography Artifacts using Gradient Projection and Flash-Exposure Sampling
Computer Vision

 

Project Description:
  Flash images are known to suffer from several problems: saturation of nearby objects, poor illumination of distant objects, reflections of objects strongly lit by the flash and strong highlights due to the reflection of flash itself by glossy surfaces. We propose to use a flash and no-flash (ambient) image pair to produce better flash images. A novel gradient projection scheme based on a gradient coherence model that allows removal of reflections and highlights from flash images is presented.
This project will require in-house implementation of the paper "Removing Photography Artifacts using Gradient Projection and Flash-Exposure Sampling" and demonstartion that it works. Additional application may be rquired.

Project Details:
 
  1. Supervisors:
    Dr. Yoav Schechner
    Phone: 04-8293236
    Email: yoav@ee.technion.ac.il

    Efim Koreban
    Phone: 04-8295743
    Email: fima@tx.technion.ac.il

  2. Field:
    Computer Vision
  3. Requirements:
    Image Processing course and MATLAB programming skills.
  4. Project status:
    Taken by the students Uri Dalal and Ilya Leitus
 
Current Projects Archive
CG&M Lab    Contact Us EE Labs EE Department Technion