AI algorithm unblurs the cosmos Tool produces faster, more realistic images than current methods Date: March 31, 2023 Source: Northwestern University Summary: Researchers adapted a well-known ...

Researchers at Monash University have designed a new co-training AI algorithm for medical imaging that can effectively mimic the process of seeking a second opinion.

Researchers have developed a novel attack that steals user data by injecting malicious prompts in images processed by AI ...

The use of artificial intelligence (AI) in medical care is a salient example of the technology’s value. Yet AI’s improvements may be marginal and may also introduce downsides, such as higher costs and ...

While astrophysicists already use technologies to remove blur, the adapted AI-driven algorithm works faster and produces more realistic images than current technologies.

A two-year study using AI-based satellite imagery has concluded that the number of wildebeests migrating annually across the Serengeti-Mara ecosystem is less than 600,000. This figure is only half of ...

Recent research into methods for spotting AI-generated video looks for specific markers not found in standard digital images.

Image classification algorithms are notoriously error-prone, but a novel method for spotting errors within incomprehensible AI code could help solve the problem.

Facebook's researchers have achieved a breakthrough in self-supervised learning, by training an AI system on one billion unlabeled Instagram pictures.

The AI algorithm can produce detailed geometry from a video or a shape image, preserving complex textures like wood grains.