Reproduce “Complexity-Calibrated Reconstruction Discrepancy for No-Reference Point Cloud Quality Assessment” 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
Haocheng Wu, Xiangjie Sui, Xin Sun
The authors introduce a no-reference point-cloud quality assessment method using successive reconstructions to estimate a content-dependent calibration cue. It subtracts a weighted discrepancy between first and smoothed second reconstructions from the initial discrepancy, combining 3D geometry and projected 2D appearance cues. On SJTU-PCQA, it reaches SRCC 0.721 and PLCC 0.739, exceeding LIQE, but calibration does not improve every metric.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.