Reproduce “From Geometry to Function: A Multi-Task LiDAR Benchmark Dataset for Semantic and Functional Parsing of Urban Facades” 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
Abdiaziz Muse, Tooba Javed, Tao Pu, Jiju Poovvancheri, Dong Chen
The authors introduce HFX3D, a facade LiDAR benchmark that labels each point’s class, groups points into instances, and assigns instance-level functions. It contains about 492 million points from 26 Halifax buildings, with 12 semantic classes and 15 attributes. KPConv reaches 47.26% test mIoU; on ambiguous instances, geometry-only macro-F1 exceeds the full evidence combination, so function prediction remains difficult.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.