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

arXiv:2610.11653 · cs.GR, cs.CV · Submitted 2026-10-08 · Read on arXiv

cs.GR, cs.CV

Submitted: 2026-10-08

Updated: 2026-10-08

Code: https://github.com/facebookresearch/Tabula-Rasa

Terminology

• Monte Carlo — 27× in this paper
• Diffusion Model — 13× in this paper · explained in 8 episodes
• Optical Flow — 13× in this paper · explained in 2 episodes
• Consistency — 9× in this paper · explained in 3 episodes
• Diffusion Models — 8× in this paper · explained in 6 episodes
• Temporal consistency — 7× in this paper · explained in 2 episodes
• Generative Model — 3× in this paper · explained in 2 episodes
• Downstream Tasks — 2× in this paper · explained in 2 episodes
• ACM Transactions on Graphics — 1× in this paper
• Adam — 1× in this paper · explained in 2 episodes
• Core — 1× in this paper · explained in 2 episodes
• Cosine Similarity — 1× in this paper · explained in 3 episodes
• Fidelity — 1× in this paper · explained in 2 episodes
• Generative Models — 1× in this paper · explained in 2 episodes
• Latent Space — 1× in this paper · explained in 7 episodes
• Prompt Adherence — 1× in this paper · explained in 2 episodes
• Quasi-Monte Carlo — 1× in this paper
• Temporal Correlations — 1× in this paper · explained in 2 episodes

Sources

• CoTracker3: Simpler and Better Point Tracking by Pseudo-Labelling Real Videos
• The 2017 DAVIS Challenge on Video Object Segmentation

Related papers

• SCRIPT: Scalable Diffusion Policy with Multi-stage Training for Language-driven Physics-Based Humanoid Control
• CADReasoner: Iterative Program Editing for CAD Reverse Engineering
• QuadLink: Autoregressive Quad-Dominant Mesh Generation via Point-Relation Learning
• DrawVideo: Grounded and Faithful Multi-Shot Video Generation from Storyboard Keyframe Sketches
• MotionPersona: Real-Time Locomotion Control across Personas, Bodies, and Styles
• MeshSplatBench: A Unified Benchmark for Triangle- and Mesh-Based Neural Rendering