Tabula Rasa: Monte Carlo estimation of unit-variance noise with controlled spatio-temporal correlation
Tobias Ritschel, Yang Zhou, Nick Milef, Mikhail Dereviannykh, Chen Liu, Christophe Hery, Carl Marshall
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.
Create a lesson
Related papers
3DRAG: 3D-Native Object Drag Editing with Generative Models
Kuixiang Shao, Yuyang Jiao, Chenghao Zhang et al.
FeatureZ: A General Framework for Feature-Preserving Compression via Pointwise Bounds and Star Classification
Nathaniel Gorski, Xin Liang, Hanqi Guo et al.
SubDGuide: A Modeler-Inspired Agentic Workflow for Mesh-to-SubD Reconstruction
Mengnan Jiang, Christian Franke, Michele Franco Adesso et al.
Neural Caching of Prefiltered Radiance for Specular Lighting
Dmitrii Klepikov, Vladimir Frolov
Sensitivity as an Arbitrary Output Variable for Differentiable Rendering
Linas Beresna, Eugene Fiume
Stochastic Graph Compression for Constant-Memory Differentiable Light Tracing
Linas Beresna, Eugene Fiume