A New Trick Lets Artificial Intelligence See in 3D | WIRED
wired.com · 1,291 words · saved by 1 readers
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
- Neural radiance field - Wikipediaen.wikipedia.org
- Building NeRF at City Scaleneuralfields.cs.brown.edu
- D-NeRF: Neural Radiance Fields for Dynamic Scenesopenaccess.thecvf.com
- The flavor of the bitter lesson for computer vision - Vincent Sitzmannvincentsitzmann.com
- Machine Learning for Inverse Graphics – Scene Representation Groupscenerepresentations.org
- VastGaussian: Vast 3D Gaussians for Large Scene Reconstruction | PDFarxiv.org
- NeRF Explosion 2020 - Frank Dellaertdellaert.github.io
- 3D as code | World Labsworldlabs.ai
- InseRF: Text-Driven Generative Object Insertion in Neural 3D Scenesmohamad-shahbazi.github.io
- InseRF: Text-Driven Generative Object Insertion in Neural 3D Scenesarxiv.org
- World Emulation via Neural Networkmadebyoll.in