We may soon live in a world where it is hard to tell whether the person speaking to us in a video is real or generated by a computer program. That’s something to ponder. Here’s something else: Google researchers have unveiled an AI that can bring still photos to life. You heard me right. It’s called “VLOGGER”. I thought a VLOGGER was someone who posts videos to a vlog which is a video blog. However, Google has developed an artificial intelligence system that can generate lifelike videos of people speaking, gesturing and moving ….from just a single still photo. This technology opens up a range of potential applications while also raising concerns about deepfakes and misinformation. Google’s AI model takes a still photo and an audio clip, and then puts out a video that matches the audio showing the person speaking the words and making corresponding facial expressions, head movements and hand gestures. The method generates the complete image of the person in the photograph, not just the face or lips. So far, VLOGGER still has limitations though. Mannerisms and speech patterns, while realistic, aren’t yet indistinguishable from those of real humans. However, with further advances to this type of AI-generated media, I’ll repeat what I said: We may soon live in a world where it is hard to tell whether the person speaking to us in a video is real or generated by a computer program. VLOGGER is a sign of the challenges we will face in determining what is real and what is fake.
That’s Coffeetalk. I’m Vic Dubois.