Business Standard

Wednesday, December 25, 2024 | 12:47 AM ISTEN Hindi

Notification Icon
userprofile IconSearch

Google unlocks Pixel 2's AI-based semantic image technology for developers

With this public release, the search engine giant hopes to make it easier for other groups in academia and industry to reproduce and further improve state-of-the-art systems

Google Semantic image segmentation
Premium

Google Semantic image segmentation

Khalid Anzar New Delhi
Search engine and software giant Google, a has open-sourced its artificial intelligence-based ‘Semantic Image Segmentation’ technology – a technology used in the Pixel 2 and Pixel 2 XL portrait mode to achieve shallow depth-of-field effect without the need for a secondary camera.

“Today, we are excited to announce the open-source release of our latest and best-performing semantic image segmentation model, DeepLab-v3+, implemented in Tensorflow. This release includes DeepLab-v3+ models built on top of a powerful convolutional neural network (CNN) backbone architecture for the most accurate results, intended for server-side deployment. As part of this release, we are additionally sharing our Tensorflow

What you get on BS Premium?

  • Unlock 30+ premium stories daily hand-picked by our editors, across devices on browser and app.
  • Pick your 5 favourite companies, get a daily email with all news updates on them.
  • Full access to our intuitive epaper - clip, save, share articles from any device; newspaper archives from 2006.
  • Preferential invites to Business Standard events.
  • Curated newsletters on markets, personal finance, policy & politics, start-ups, technology, and more.
VIEW ALL FAQs

Need More Information - write to us at assist@bsmail.in