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.
-
-
Articles récents
- End-to-End Podcast Generation Using OpenNotebook on Intel® Xeon®: A Practical Guide
- ExecuTorch with OpenVINO Backend in 2026: New Capabilities and Updates
- Gemma 4 Models optimized for Intel Hardware: Enabling instant deployment from day zero
- Why Planning is the Most Crucial Step for Enterprise AI Readiness
- Saturate your Tensor Cores: Intel at NVIDIA GTC 2026
-
Neural networks news
Intel NN News
-