Reproduce “Shape Modeling with Spline Partitions” 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
Shufei Ge, Shijia Wang, Lloyd Elliott
SMSP models two-dimensional shapes by recursively partitioning an image with randomly proposed Bézier curves rather than straight cuts. The authors test it on synthetic shapes and macrophage masks. In a one-cut yin-yang task, cubic-curve SMSP averages 90.19% correct versus 88.59% for RTP, while a radial-kernel SVM scores 96.67%; the results do not establish biological perimeter validation or performance beyond two dimensions.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.