London: A new technique has been developed by a programmer that lets fakers add anything to photos in minutes and give “real-looking” results by simply drawing a few lines on the screen.
According to Kevin Karsch, a PhD student at the University of Illinois and the creator of the new “super Photoshop”, even “novice” users can achieve “professional results” with the use of this technique.
Karsch describes his software as “a method to realistically insert synthetic objects into existing photographs without requiring access to the scene, special equipment, multiple photographs, time lapses, or any other aids.”
He also said that while it’s easy to digitally remove objects from scenes, it’s much harder to insert them without people spotting that something’s up.
“Currently, to insert objects into the scene, some geometry must be manually created, and lighting models often use mirrored light probes placed in the scene, taking multiple photographs of the scene, or even modeling the sources manually,” the Daily Mail quoted Karsch as saying.
“Either way, the process is painstaking and requires expertise,” he said.
The software automatically builds a rough 3D model of a scene and users just have to add any surfaces it might have missed, by drawing on screen.
“Next, the user annotates light sources and light shafts strongly directed light in the image. Our system automatically generates a physical model of the scene using these annotations,” Karsch said.
The software then adds light as it can deal even with shiny, reflective or “glowing” synthetic objects.
“Our method only needs a few quick annotations, allowing novice users to create professional quality results.
“ The results achieved by our method appear realistic, and people tend to favour our synthetic renderings over other insertion methods,” he added.