AI model speeds up high-resolution computer vision

Using AI to improve image quality in video streaming and autonomous vehicle hazard identification.

Jon Peddie

Researchers from MIT and the MIT-IBM Watson AI Lab have developed an efficient computer vision model for autonomous vehicles and other high-resolution computer vision tasks. This model, called EfficientViT, performs real-time semantic segmentation with linear computational complexity, outperforming previous models by running up to nine times faster while maintaining accuracy. It simplifies the attention map construction and balances performance and efficiency by adding components for capturing local features and multiscale learning. The model’s hardware-friendly design makes it adaptable to various devices, including autonomous vehicles, virtual reality headsets, and edge computers. It holds the potential to improve real-time decision-making and efficiency

Enjoy full access with a TechWatch subscription!

TechWatch is the front line of JPR information gathering service, comprising current stories of interest to the graphics industry spanning the core areas of graphics hardware and software, workstations, gaming, and design.

A subscription to TechWatch includes 4 hours of consulting time to be used over the course of the subscription.

Already a subscriber? Login below

This content is restricted

Subscribe to TechWatch