Reproduce “GenZ-LIO: Generalizable LiDAR-Inertial Odometry Beyond Confined--Open Boundaries” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Daehan Lee, Hyungtae Lim, Seongjun Kim, Soonbin Rho, Changhyeon Lee, Sanghyun Park, Junwoo Hong, Eunseon Choi and 2 more
GenZ-LIO adapts LiDAR-inertial odometry to changing scene scales by varying its point-count target and combining point-to-plane and point-to-point constraints with reliability-based weighting. Across 42 sequences from nine public datasets and NarrowWide, it reports a 0.00% total divergence rate and a lowest total average rank of 1.67, versus 6.57 for PV-LIO. These results apply to tested sequences and protocol; they measure translational error, not rotational accuracy.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.