Research map / Image generation / Fast diffusion sampling
Incomplete Data, Complete Dynamics: A Diffusion Approach
Zihan Zhou, Chenguang Wang, Hongyi Ye, Yongtao Guan, Tianshu Yu
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 |
|---|---|---|---|
| Use block-wise context-query partitioning matching block masks instead of pixel-level (ablation) | context-query diffusion · Navier-Stokes 8/9 blocks | error: 1.4925 -> 0.7592 | Improved |
| Use block-wise instead of pixel-level partitioning (ablation) | context-query diffusion · Advection 5/9 blocks | error: 0.1894 -> 0.1407 | Improved |
| Use block-wise instead of pixel-level partitioning (ablation) | context-query diffusion · Shallow Water 5/9 blocks | error: 0.0989 -> 0.0865 | Improved |
| Train on context-query split of incomplete data vs AmbientDiff | diffusion imputation · Navier-Stokes 20% observed | MSE x1e-3: 2.043 -> 1.931 | Improved |
| Use ours vs AmbientDiff at extreme sparsity | diffusion imputation · ERA5 1% observed | MSE x1e-2: 1.234 -> 1.229 | No clear effect |
| Switch MissDiff to data matching | MissDiff baseline · physical dynamics imputation | MSE | Improved |
| Train on fewer observed points (20% instead of 80%) | Ours · Navier-Stokes test at 80% | MSE x1e-3: 0.2229 -> 0.3363 | Hurt |
| Use moderate context ratio (ablation) | Ours · physical dynamics imputation | reconstruction error | Improved |
Closest papers by meaning
- Predicting partially observable dynamical systems via diffusion models with a multiscale inference scheme (NeurIPS 2025 · similarity 0.90)
- Zero-shot Imputation with Foundation Inference Models for Dynamical Systems (ICLR 2025 · similarity 0.89)
- Generating Full-field Evolution of Physical Dynamics from Irregular Sparse Observations (NeurIPS 2025 · similarity 0.88)
- On conditional diffusion models for PDE simulations (NeurIPS 2024 · similarity 0.87)
- ABC: Any-Subset Autoregression via Non-Markovian Diffusion Bridges in Continuous Time and Space (NeurIPS 2026 · similarity 0.87)
- Consistent Diffusion Meets Tweedie: Training Exact Ambient Diffusion Models with Noisy Data (ICML 2024 · 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.
