Skip to main content

The latest research from Google

Scalable spherical CNNs for scientific applications

Typical deep learning models for computer vision, like convolutional neural networks (CNNs) and vision transformers (ViT), process signals assuming planar (flat) spaces. For example, digital images are represented as a grid of pixels on a plane. However, this type of data makes up only a fraction of the data we encounter in scientific applications. Variables sampled from the Earth's atmosphere, like temperature and humidity, are naturally represented on the sphere. Some kinds of cosmological data and panoramic photos are also spherical signals, and are better treated as such.

Google at ICCV 2023

DynIBaR: Space-time view synthesis from videos of dynamic scenes

Re-weighted gradient descent via distributionally robust optimization

Google Research embarks on effort to map a mouse brain

Distilling step-by-step: Outperforming larger language models with less training data and smaller model sizes

MediaPipe FaceStylizer: On-device real-time few-shot face stylization

On-device content distillation with graph neural networks

World scale inverse reinforcement learning in Google Maps

Differentially private median and more

A novel computational fluid dynamics framework for turbulent flow research