Computer graphics researchers at Carnegie Mellon University have developed systems for editing or altering photographs using segments of the millions of images available on the Web.
Whether adding people or objects to a photo, or filling holes in an edited photo, the systems automatically find images that match the context of the original photo so they blend realistically. Unlike traditional photo editing, these results can be achieved rapidly by users with minimal skills.
“We are able to leverage the huge amounts of visual information available on the Internet to find images that make the best fit,” said Alexei A. Efros, assistant professor of computer science and robotics. “It’s not applicable for all photo editing, such as when an image of a specific object or person is added to a photo. But it’s good enough in many cases,” he added. “Why Photoshop if you can ‘photoswap’ instead?”
Efros and his colleagues will present papers on two related systems at the Association for Computing Machinery’s Special Interest Group on Graphics and Interactive Techniques (SIGGRAPH) annual conference Aug. 5–9 in San Diego.
One system, called Photo Clip Art (
http://graphics.cs.cmu.edu/projects/photoclipart/), was developed with graduate students Jean-François Lalonde and Derek Hoiem, and with Carsten Rother, John Winn and Antonio Criminisi of Microsoft Research Cambridge. It uses thousands of labeled images from a Web site called LabelMe as clip art that can be added to photos. A photo showing a vacant street, for instance, might be populated with images of people, vehicles and even parking meters derived from the LabelMe database (
http://labelme.csail.mit.edu/).
To make the resulting image appear as realistic as possible, the system analyzes the original photo to estimate the camera angle and lighting conditions, and then looks in the clip art library for an object — a car, for instance — that matches those criteria. The user need only identify the horizon in the original photo to orient the system. Using previously developed Carnegie Mellon technology for analyzing the geometric context of a photo, the system can then place the object within the scene, adjusting its size as necessary to put it in proportion to other objects of equal distance from the camera.
“Matching an object with the original photo and placing that object within the 3-D landscape of the photo is a complex problem,” said Lalonde, who led development of the system. “But with our approach, and a lot of clip art data, we can hide the complexity from the user and make the process simple and intuitive.”
The other system, called Scene Completion (
http://graphics.cs.cmu.edu/projects/scene-completion/), was developed by graduate student James Hays, another member of Efros’ research team. It draws upon millions of photos from the Flickr Web site to fill in holes in photos. Some of the holes might be from damage to a physical photograph, but more often they are created when an editor cuts out part of an image to eliminate an unsightly truck from a picturesque street scene, or removing a passerby from a group shot of friends. Photo editors often try to fill in those holes with sections derived elsewhere in the same image, but Efros said that a better match can often be found in a different photo.
The system looks for image segments that match the colors and textures that surround the hole on the original photo. It also looks for image segments that make sense contextually — in other words, it wouldn’t put an elephant in a suburban backyard or a boat in a desert.
In the case of well-photographed cities or popular tourist attractions, Efros said, the system might get lucky and find a photo of the same scene on the Web. In other cases, it might offer a number of possible images that could fill in the hole. A retaining wall edited out of one photo, for instance, might be replaced by the image of a building, a grassy slope or a rock outcropping. The system typically gives the user 20 different choices for filling in the hole.
The success of this approach depends on the number of photos available to the system, Hays said. “We saw a dramatic improvement when we moved from a database of 10,000 images to two million images,” he noted. “And that is just a tiny fraction of the hundreds of millions of images already available on sites like Picasa and Flickr. We have tons of photos from which to choose.”
Source: Carnegie Mellon University
Related stories:
Trendy gadget gifts -- but just in case, hang onto receipts
Buying high-tech gifts is really hard. It's almost impossible to keep abreast of the latest gadgets and know which ones are getting long in the tooth.
Flickr revamps its mobile video-sharing features
Flickr on Thursday began rolling out "radically overhauled" mobile video-sharing features that make the popular website more social and easier to use on the move.
Saying 'Cheese' for More Effective Border Security
Facial recognition systems perform some very challenging tasks such as checking an individual’s photo against a database of known or suspected criminals. The task can become nearly impossible when the systems acquire poor facial images—a situation that occurs all too often in real-world environments. Now, researchers at the National Institute of Standards and Technology have found that several simple steps can significantly improve the quality of facial images that are acquired at border entry points such as airports and seaports.
Extreme makeover: computer science edition
(PhysOrg.com) -- Suppose you have a cherished home video, taken at your birthday party. You're fond of the video, but your viewing experience is marred by one small, troubling detail. There in the video, framed and hanging on the living room wall amidst the celebration, is a color photograph of your former significant other.
Software for safe bridges
Spanning deep gorges, rivers and freeways, bridges are an indispensable part of the traffic network. Yet their condition in Germany is appalling: In a survey carried out by the German automobile club ADAC in 2007, one in ten bridges out of the fifty that were inspected failed the test; a total of four were rated "poor" and one was even rated "very poor". The changing effects of weather and temperature, road salt and the increasing volume of traffic all take their toll on the material – quickly causing damage such as hairline cracks, flaking concrete, and rust penetration. If the bridge engineers fail to recognize these in time, motorists, cyclists and pedestrians are endangered.
Mastering your camera can help your brain
You know you have to add mental exercise to your daily activities if you're going to live to a healthy and happy old age.
A Picture is Worth a Thousand Locksmiths, Computer Scientists Say
(PhysOrg.com) -- UC San Diego computer scientists have built a software program that can perform key duplication without having the key. Instead, the computer scientists only need a photograph of the key.
Frames are a picture of high-tech charm
Sharing photos is pretty easy these days, with Web sites such as Flickr and Facebook becoming a depository for our images and memories.