no code implementations • 23 Apr 2023 • Wanting Li, Yu Shao, Yongcai Wang, Shuo Wang, Xuewei Bai, Deying Li
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.
1 code implementation • 25 Mar 2023 • Hongyu Sun, Yongcai Wang, Xudong Cai, Xuewei Bai, Deying Li
For example, the image branch in CrossPoint is $\sim$8. 3x heavier than the point cloud branch leading to higher complexity and latency.