Image Melding: Combining Inconsistent Images
using Patch-based Synthesis


Proceedings of SIGGRAPH 2012

ACM Transactions on Graphics (TOG)
Vol. 31, No. 4, Art. 82, July 2012

       Soheil Darabi1           Eli Shechtman2           Connelly Barnes2           Dan B Goldman2           Pradeep Sen1  

1 UNM Advanced Graphics Lab        2 Adobe      

Abstract

Current methods for combining two different images produce visible artifacts when the sources have very different textures and structures. We present a new method for synthesizing a transition region between two source images, such that inconsistent color, texture, and structural properties all change gradually from one source to the other. We call this process image melding. Our method builds upon a patch-based optimization foundation with three key generalizations: First, we enrich the patch search space with additional geometric and photometric transformations. Second, we integrate image gradients into the patch representation and replace the usual color averaging with a screened Poisson equation solver. And third, we propose a new energy based on mixed L2/L0 norms for colors and gradients that produces a gradual transition between sources without sacrificing texture sharpness. Together, all three generalizations enable patch-based solutions to a broad class of image melding problems involving inconsistent sources: object cloning, stitching challenging panoramas, hole filling from multiple photos, and image harmonization. In several cases, our unified method outperforms previous state-of-the-art methods specifically designed for those applications.


The Paper


The Video

Image Melding: Combining Inconsistent Images using Patch-based Synthesis

Additional Materials


Bibtex

@article{Darabi12:ImageMelding12,

author = {Soheil Darabi and Eli Shechtman and Connelly Barnes

and Dan B Goldman and Pradeep Sen},

title = {{I}mage {M}elding: Combining Inconsistent Images using Patch-based Synthesis},

journal = {ACM Transactions on Graphics (TOG) (Proceedings of SIGGRAPH 2012)},

volume = {31},

number = {4},

articleno = {82},

pages = {82:1--82:10},

year = {2012},

}





This page contains documents, source code, videos and other files that could be protected by copyright. They are provided here for reasonable academic fair use. Interested parties are referred to the official published version of the documents which are available from the copyright holder through the external link.