3D Virtual Images are Becoming So Realistic that Humans Have a Hard Time Telling the Difference

People may be having a harder time telling the difference between what's real and what's virtual. Scientists have found that people find it increasingly difficult to distinguish between computer-generated images and real photos, but that a small amount of training greatly improves their accuracy.

The 3D rendering software and hardware that computers use is becoming more and more powerful. In addition, the computer-generated characters that these programs create for film making, video games and advertising and other venues have become more photo-realistic. As these tools become more powerful, it's important to be able to determine the difference between virtual reality and actual reality, especially for legal issues.

"As computer-generated images quickly become more realistic, it becomes increasingly difficult for untrained human observers to make this distinction between the virtual and the real," said Hany Farid, one of the researchers, in a news release. "This can be problematic when a photograph is introduced into a court of law and the jury has to assess its authenticity."

In this latest study, the researchers conducted perceptual experiments in which 60 high-quality computer-generated and photographic images of men's and women's faces were shown to 250 observers. Each observer was asked to classify each image as either computer generated or photographic.

So what did they find? The observers correctly classified photographic images 92 percent of the time, but correctly classified computer-generated images only 60 percent of the time.

In a follow-up experiment, the researchers provided training to the observers, and found that their accuracy on classifying photographic images fell slightly to 85 percent, but their accuracy on computer-generated images jumped to 76 percent.

"We expect that as computer-graphics technology continues to advance, observers will find it increasingly difficult to distinguish computer-generated from photographic images," said Farid. "While this can be considered a success for the computer-graphics community, it will no doubt lead to complications for the legal and forensic communities. We expect that human observers will be able to continue to perform this task for years to come, but eventually we will have to refine existing techniques and develop new computational methods that can detect fine-grained image details that may not be identifiable by the human visual system."

The findings are published in the journal ACM Transactions on Applied Perception.

Related Articles

Environmental Performance Index Ranks World's Top and Worst Performers

Pesticides and Lung Capacity: They May Affect Your Child's Breathing (VIDEO)

For more great science stories and general news, please visit our sister site, Headlines and Global News (HNGN).