Reproduce “Superquadric Primitive Decomposition of 3D point clouds via Geometric-Aware Inlier Refinement” 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
Alessandro Rinaldi, Edoardo Tedesco, Andrea Ferraris, Filippo Leveni, Daniele Baieri, Filippo Maggioli, Simone Melzi, Luca Magri
The paper introduces GAIR-RANSAC, which fits superquadrics by combining model distance and surface-normal cues in graph-cut inlier refinement. Its multi-model wrapper selects candidates by coverage. On four intertwined synthetic superquadrics with σ = 0.1 noise and 4,000 outliers, it reports CD 0.27, HD 0.59, and IAE 0.03, outperforming GC-RANSACOV, but relies on usable normals and a specified primitive count.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.