Reproduce “PlenoCI: Plenoptic CharacterIstics for View Dependence Aware Change Classification” 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
Jason Lai, Chamuditha Jayanga Galappaththige, Niko Suenderhauf, Dimity Miller, Donald G. Dansereau
PlenoCI measures changes in light as a ray’s position or direction shifts, deriving plenoptic derivatives from 3D Gaussian Splatting models. It uses these signals to identify visual structures, including occlusion edges, while also responding to reflections and specularity. In unchanged-scene reconstructions on PASLCD, the method reports a 0.004% false-positive rate versus GS-Diff’s 0.389%, but sparse view coverage raises false positives.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.