Toggle light / dark theme

Summary: Researchers in China have developed a new neural network that generates high-quality bird images from textual descriptions using common-sense knowledge to enhance the generated image at three different levels of resolution, achieving competitive scores with other neural network methods. The network uses a generative adversarial network and was trained with a dataset of bird images and text descriptions, with the goal of promoting the development of text-to-image synthesis.

Source: Intelligent Computing.

In an effort to generate high-quality images based on text descriptions, a group of researchers in China built a generative adversarial network that incorporates data representing common-sense knowledge.

Physicists believe most of the matter in the universe is made up of an invisible substance that we only know about by its indirect effects on the stars and galaxies we can see.

We’re not crazy! Without this “dark matter”, the universe as we see it would make no sense.

But the nature of dark matter is a longstanding puzzle. However, a new study by Alfred Amruth at the University of Hong Kong and colleagues, published in Nature Astronomy, uses the gravitational bending of light to bring us a step closer to understanding.

Organoids aren’t nearly as complex as their full-sized counterparts, but they’re useful for research — scientists can study organ development, monitor disease progression, and even test new treatments on them.

What’s new: When human embryos are about five weeks old, they develop structures called “optic cups” that will eventually become retinas.

Researchers have grown optic cups in the lab before, and they’ve also grown mini brains. Now, researchers at University Hospital Düsseldorf have grown brain organoids with optic cups.