Perspective (In)consistency of Paint by Text
This addresses the problem of detecting AI-generated images for forensic analysts, though it is an incremental exploration of existing methods applied to new data.
The paper investigates the perspective consistency of DALL-E-2 synthesized images to assess if geometric-based forensic methods can detect this synthetic media, finding that these images often contain geometric inconsistencies that could aid in detection.
Type "a sea otter with a pearl earring by Johannes Vermeer" or "a photo of a teddy bear on a skateboard in Times Square" into OpenAI's DALL-E-2 paint-by-text synthesis engine and you will not be disappointed by the delightful and eerily pertinent results. The ability to synthesize highly realistic images -- with seemingly no limitation other than our imagination -- is sure to yield many exciting and creative applications. These images are also likely to pose new challenges to the photo-forensic community. Motivated by the fact that paint by text is not based on explicit geometric modeling, and the human visual system's often obliviousness to even glaring geometric inconsistencies, we provide an initial exploration of the perspective consistency of DALL-E-2 synthesized images to determine if geometric-based forensic analyses will prove fruitful in detecting this new breed of synthetic media.