Reproduce “Tabula Rasa: Monte Carlo estimation of unit-variance noise with controlled spatio-temporal correlation” 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
Tobias Ritschel, Yang Zhou, Nick Milef, Mikhail Dereviannykh, Chen Liu, Christophe Hery, Carl Marshall
Tabula Rasa estimates pixel values and variance loss during Monte Carlo reconstruction to correlate noise with motion in video sequences while targeting unit variance. It tracks sample contributions with a compact histogram sketch and rescales each reconstructed pixel. In video super-resolution tests, its 3D temporal-consistency score was 706.25, versus 766.99 for Go-with-the-Flow, though their flow representations differ.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.