Tabula Rasa: Monte Carlo estimation of unit-variance noise with controlled spatio-temporal correlation

Tobias Ritschel, Yang Zhou, Nick Milef, Mikhail Dereviannykh, Chen Liu +2 more
10/8/2026
cs.GRcs.CV

No official code found. Best implementation: facebookresearch/Tabula-Rasa (1 star, last commit 2026-09-13).

Abstract

We suggest a method to generate time-varying Gaussian noise with controlled variance and controlled temporal correlation. This noise is used in several downstream tasks for temporal control and temporal coherence. The core technical idea is to phrase this problem as joint Monte-Carlo estimation of both a classic pixel reconstruction and estimation of variance using the concept of "sketching" from the database literature. We demonstrate that our method allows temporal control for downstream tasks with simpler and faster code than previous methods.

View on arXivView PDF

Code Implementations(1)

facebookresearch/Tabula-RasaCommunity71%

Official source code for "Tabula Rasa Monte Carlo estimation of unit-variance noise with controlled spatio-temporal correlation"

10Sep 10, 20261 months agoNOASSERTION

Similar Papers

Go-with-the-Flow: Motion-Controllable Video Diffusion Models Using Real-Time Warped Noise

76% match3 repos1.1k2026

How I Warped Your Noise: a Temporally-Correlated Noise Prior for Diffusion Models

75% match2026

Go-with-the-Flow: Motion-Controllable Video Diffusion Models Using Real-Time Warped Noise

75% match2 repos1.1k2025

Adaptive Noise Covariance Estimation under Colored Noise using Dynamic Expectation Maximization

74% match2023

Does Vector Quantization Fail in Spatio-Temporal Forecasting? Exploring a Differentiable Sparse Soft-Vector Quantization Approach

74% match1 repo112023

POp-GS: Next Best View in 3D-Gaussian Splatting with P-Optimality

74% match2026

Cite this paper

@article{ritschel2026tabula,
  title  = {Tabula Rasa: Monte Carlo estimation of unit-variance noise with controlled spatio-temporal correlation},
  author = {Tobias Ritschel and Yang Zhou and Nick Milef and Mikhail Dereviannykh and Chen Liu and Christophe Hery and Carl Marshall},
  year   = {2026},
  eprint = {2610.11653},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2610.11653v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2610.11653.svg)](https://codeofpaper.com/paper/2610.11653)

Discussion