Reproduce “Complex-Object Visual Inspection via Multiple Lighting Configurations” 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
Maya Aghaei, Matteo Bustreo, Pietro Morerio, Nicolo Carissimi, Alessio Del Bue, Vittorio Murino
The authors use one camera and four lighting configurations at three exposure times to capture twelve views of each region. Annotators could visualize and correctly label 99.2% of defects in a freely selected collection of complex-objects. In multi-view evaluation, late fusion raises AP from 52.08 to 60.84 at IoU 0.5; at confidence 0.7, recall rises while precision falls.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.