New AI method for graphing scenes from images

Generative AI programs can generate images from textual prompts. These models work best when they generate images of single objects. Creating complete scenes is still difficult. Michael Ying Yang, a UT-researcher from the faculty of ITC recently developed a novel method that can graph scenes from images that can serve as a blueprint for generating realistic and coherent images. He and his team recently published their findings in the journal IEEE Transactions on Pattern Analysis and Machine Intelligence.

from Tech Xplore - electronic gadgets, technology advances and research news https://ift.tt/CDhHfKE

Comments

Popular posts from this blog

Space-based experiments show wax-filled heat sinks keep electronics cooler for longer

Extending the lifespan of lithium-metal batteries using a fluorinated ether diluent

First open-source tool to let planners map pedestrian networks