By enabling models to see the world more like humans do, the work could help improve driver safety and shed light on human behavior.
William Freeman
-
Researchers enhance peripheral vision in AI models
-
Study: Smart devices’ ambient light sensors pose imaging privacy risk
The ambient light sensors responsible for smart devices’ brightness adjustments can capture images of touch interactions like swiping and tapping for hackers.
-
Researchers use AI to identify similar materials in images
This machine-learning method could assist with robotic scene understanding, image editing, or online recommendation systems.
-
A new state of the art for unsupervised vision
MIT CSAIL scientists created an algorithm to solve one of the hardest tasks in computer vision: assigning a label to every pixel in the world, without human supervision.
-
Technique enables real-time rendering of scenes in 3D
The new machine-learning system can generate a 3D scene from an image about 15,000 times faster than other methods.
-
Recovering “lost dimensions” of images and video
Model could recreate video from motion-blurred images and “corner cameras,” may someday retrieve 3D data from 2D medical images.
-
Magnifying Vibrations in Bridges and Buildings, William Freeman
