Search papers, labs, and topics across Lattice.
Karlsruhe Institute of Technology
2
0
4
Panoramic vision-language models can achieve a level of holistic scene understanding and robustness in adverse conditions that's impossible for traditional pinhole-based VLMs.
Autonomous vehicles can now better "see" the world even when cameras fail, thanks to a new method that fills in the blanks by leveraging spatial overlaps and learned semantic priors.
