Search Results for author:
Found 2 papers, 1 papers with code
IDLL: Inverse Depth Line based Visual Localization in Challenging Environments
In this paper, we propose Inverse Depth Line Localization(IDLL), which models each extracted line feature using two inverse depth variables exploiting the fact that the projected pixel coordinates on the image plane are rather accurate, which partially restrict the lines.
ViPFormer: Efficient Vision-and-Pointcloud Transformer for Unsupervised Pointcloud Understanding
For example, the image branch in CrossPoint is $\sim$8. 3x heavier than the point cloud branch leading to higher complexity and latency.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
