Reproduce “Aerial Content-Aware Sample-Adaptive Classifier for Urban Photogrammetric Point Cloud Segmentation” 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
Chong Liu, Yonghua Lu, Zhanglin Cheng
ACASAC adapts broad aerial context and local point features to classify each urban point-cloud patch. It compares scene-level and locally aligned aerial representations, then transfers those relations to refine point-class prototypes alongside a fixed classifier prior. It reaches 68.2% mean intersection-over-union on SensatUrban and 75.2% on UrbanBIS, improving over matched fixed heads in these evaluated settings.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.