Researchers have developed an AI tool that can turn blurry faces into eerily convincing computer-generated portraits, in finer detail than ever before. Previous methods can scale an image to eight times its original resolution. But a Duke team has come up with a way to take a handful of pixels and create realistic-looking faces with up to 64 times the resolution, ‘imagining’ features such as eyelashes and stubble that weren’t there in the first place.
- UMD-led study shows fear and anxiety share same bases in brain
- Patients who had more severe covid-19 may be the best donors for convalescent plasma therapy
- Astrophysics team lights the way for more accurate model of the universe
- Tropical cyclones moving faster in recent decades
- Untreated sleep apnea is associated with flu hospitalization