A New Trick Lets Artificial Intelligence See in 3D | WIRED

Some algorithms can now compose a 3D scene from 2D images—creating possibilities in video games, robotics, and autonomous driving.

Save this story Save this story The AI Database → Application Robotics Games Autonomous driving Company Nvidia End User Research Big company Sector Research Source Data Images Technology Machine vision Neural Network The current wave of artificial intelligence can be traced back to 2012, and an academic contest that measured how well algorithms could recognize objects in photographs. That year, researchers found that feeding thousands of images into an algorithm inspired loosely by the way neurons in a brain respond to input produced a huge leap in accuracy . The breakthrough sparked an explos

related reading

• NeRF: Neural Radiance Fieldsmatthewtancik.com
• The World Inside Neural Networksgoodfire.ai
• Using reflections to see the world from new points of view | MIT News | Massachusetts Institute of Technologynews.mit.edu
• The flavor of the bitter lesson for computer vision - Vincent Sitzmannvincentsitzmann.com
• D-NeRF: Neural Radiance Fields for Dynamic Scenesopenaccess.thecvf.com
• Neural radiance field - Wikipediaen.wikipedia.org
• AI to Interpret Your Mindjonathanxu.com
• 3D as code | World Labsworldlabs.ai
• Machine Learning for Inverse Graphics – Scene Representation Groupscenerepresentations.org
• Learning 3D object-centric representation through predictionarxiv.org
• ReferIt3D: Neural Listeners for Fine-Grained 3D Object Identification in Real-World Scenesecva.net
• DreamGaussian: Generative Gaussian Splatting for Efficient 3D Content Creation | PDFarxiv.org