Skip to content

deepankarc/image-poisson-blending

Repository files navigation

Poisson blending

Image blending is a process of transferring an image from the source domain to the target domain while ensuring the transformed pixels conform to the target domain to ensure consistency. Poisson Image Blending was introduced by Perez et al. to perform seamless blending of images. The idea utilizes the sensitivity of human observers to gradients in an image. By exploiting this we obtain a Poisson equation the solution to which yields the algorithm for seamless blending.

This code implements gradient domain fusion of images via two techniques both of which are discussed in [1]:

  1. Poisson Blending
  2. Mixed Gradients

The results are shown below:

ScreenShot

alt text

                                      Fig.1 - Image Blending 

[1] - P. Perez, M. Ganget, A. Blake - Poisson Image Editing

About

Poisson blending of images

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published