Researchers at Intel Labs, in collaboration with Xiamen University, have presented LiSA, the first semantic aware AI framework for highly accurate 3D visual localization. LiSA can leverage pre-trained semantic segmentation models to significantly improve state-of-the-art 3D visual localization accuracy, without introducing computational overhead during inference. LiSA was presented at CVPR 2024 as a highlight paper, an award given to the top 3.6% of conference papers.
-
-
Neural networks news
Intel NN News
- Why Agentic AI is the Future of AI
The rapid advancement of AI has captured the world’s attention and accelerated the rate of […]
- How Intel® Liftoff Accelerates AI Startups
Turning an AI idea into a real product is tough. See how Intel® Liftoff gives startups the tech, […]
- Intel Presents Latest Circuit Innovations at CICC 2025
Intel is proud to present four technical papers, an educational session and panel at this year's […]
- Why Agentic AI is the Future of AI
-