Reproduce “Visibility-Aware Reference Generation for Benchmarking Visual 3D Reconstruction in Vegetation-Rich Environments” 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
Zhipeng Zhong, Matthew Coombes, Cunjia Liu
The authors turn accumulated mobile LiDAR into camera-view depth and point-cloud references without a surveyed scanner map. They accumulate scans and combine adaptive hidden-point removal with depth-gap visibility scores to filter points hidden from each camera view. On simulated data, it yields 2.9 times PSR’s density at similar AbsRel, measured only on its retained valid pixels.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.