Research map / Image generation / Fast diffusion sampling
SURGE: Approximation and Training Free Particle Filter for Diffusion Surrogate
Lifu Wei, Yinuo Ren, Naichen Shi, Yiping Lu
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add SURGE particle-filter resampling at inference to FlowDAS | FlowDAS · Lorenz 1963 | RMSE: 0.0545 -> 0.0502 | Improved |
| add SURGE to SDA | SDA · Lorenz 1963 | RMSE: 0.0589 -> 0.0555 | Improved |
| add SURGE to FlowDAS | FlowDAS · Navier-Stokes super-resolution | RMSE: 1.018 -> 0.851 | Improved |
| add SURGE to FlowDAS | FlowDAS · Navier-Stokes sparse recovery (5%) | KES-RE: 0.543 -> 0.278 | Improved |
| add SURGE to SDA | SDA · Navier-Stokes super-resolution | RMSE: 0.987 -> 0.966 | Improved |
| add SURGE to FlowDAS | FlowDAS · SEVIR VIL (10% observed) | CSI tau40: 0.4044 -> 0.4541 | Improved |
| add SURGE to SDA | SDA · SEVIR VIL (10% observed) | RMSE: 0.3511 -> 0.0925 | Improved |
| add SURGE to SDA | SDA · SEVIR VIL (10% observed) | CSI tau20: 0.2757 -> 0.4089 | Improved |
Closest papers by meaning
- FlowDAS: A Stochastic Interpolant-based Framework for Data Assimilation (NeurIPS 2025 · similarity 0.89)
- Predicting partially observable dynamical systems via diffusion models with a multiscale inference scheme (NeurIPS 2025 · similarity 0.88)
- On conditional diffusion models for PDE simulations (NeurIPS 2024 · similarity 0.88)
- Tortoise and Hare Guidance: Accelerating Diffusion Model Inference with Multirate Integration (NeurIPS 2025 · similarity 0.88)
- Nonlinear Filtering with Brenier Optimal Transport Maps (ICML 2024 · similarity 0.88)
- ABC: Any-Subset Autoregression via Non-Markovian Diffusion Bridges in Continuous Time and Space (NeurIPS 2026 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
