| Presented @ | |
Abstract
Effective resizing of images should not only use geometric constraints,
but consider the image content as well. We present a simple image operator
called seam carving that supports content-aware image resizing for both
reduction and expansion. A seam is an optimal 8-connected path of pixels
on a single image from top to bottom, or left to right, where optimality is
defined by an image energy function. By repeatedly carving out or inserting
seams in one direction we can change the aspect ratio of an image. By applying
these operators in both directions we can retarget the image to a new size.
The selection and order of seams protect the content of the image, as defined
by the energy function. Seam carving can also be used for image content
enhancement and object removal. We support various visual saliency measures for
defining the energy of an image, and can also include user input to guide the
process. By storing the order of seams in an image we create multi-size images,
that are able to continuously change in real time to fit a given size.
Paper
Acrobat PDF (~19 mb)
Video
QuickTime (~18 mb)
BibTex
@article{AS07,
author = {Shai Avidan and Ariel Shamir},
title = {Seam carving for content-aware image resizing},
journal = {ACM Trans. Graph.},
volume = {26},
number = {3},
year = {2007},
pages = {10},
publisher = {ACM},
}
* This work is patented, owned by Mitsubishi Electric Research Labs, Cambridge MA
Click on an image to view it in actual size.
 |
 |
 |
 |
Input |
Scale |
Crop |
Seam Carving |
 |
 |
 |
 |
Input |
Scale |
Crop |
Seam Carving |
 |
 |
 |
 |
|
Input |
Expanded |
Input |
Expanded |
 |
Scale |
Crop |
Seam Carving |
Input |
 |
 |
 |
Input |
50% expansion |
2-step 50% expansion |
 |
 |
 |
 |
 |
Input |
Regular Seam Carving |
Gradient Domain Seam Carving |
 |
 |
 |
Input |
Weights |
Object Removed |
Input |
 |
|
 |
 |
|
Find the Missing Shoe in each image! |
||
 |
 |
 |
|
Input |
Retargeted |
Pigeon Removed |
Girl Removed |
