Reproduce “DSOR: A Scalable Statistical Filter for Removing Falling Snow from LiDAR Point Clouds in Severe Winter Weather” 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
Akhil Kurup, Jeremy Bos
The authors introduce WADS, a LiDAR dataset with point-level labels for severe winter driving, and DSOR, a snow filter whose cutoff adapts to sensor range. On severe-snow data, DSOR removes more snow than DROR, with 95.6% recall versus 91.9%, but lower precision, 65.1% versus 71.5%. It ran faster in a runtime test; results concern filtering, not detection or driving safety.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.