Reproduce “Test-time Adaptation for Point Cloud Denoising under Unseen Noise” 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

Kun Jiang, Shida Fu, Fanhao Yi, Weiqing Li, Zhiyong Su

The authors introduce TTAD, which adapts a point-cloud denoiser to unseen test noise. It estimates each sample’s noise from residuals between the input and the denoiser’s pseudo-clean output, then uses that estimate without clean test labels. On PUNet’s 2% Pulse test, PointFilter with CTTAD lowers CD from 3.42 to 1.49 and P2M from 3.26 to 2.04; improvements are not universal.

Summary by alphaXiv.

Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.