Research map / Probabilistic and scientific modeling / Uncertainty and Gaussian processes
SNIPS: Solving Noisy Inverse Problems Stochastically
Bahjat Kawar, Gregory Vaksman, Michael Elad
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 |
|---|---|---|---|
| Average 8 posterior samples instead of using an individual sample | SNIPS · CelebA deblurring, super resolution, and compressive sensing | PSNR: around 2.4 dB | Improved |
| Use SNIPS rather than RED | Image deblurring · Deblurring | PSNR: more than 11% improvement in PSNR | Improved |
| Use SNIPS rather than RED | Image deblurring · Deblurring | LPIPS: more than 58% improvement in LPIPS | Improved |
| Use a position-dependent step-size vector derived from a diagonal Hessian approximation | SNIPS · Noisy linear inverse problems | convergence stability | Improved |
Closest papers by meaning
- The Perception-Robustness Tradeoff in Deterministic Image Restoration (ICML 2024 · similarity 0.87)
- Improving Diffusion Inverse Problem Solving with Decoupled Noise Annealing (CVPR 2025 · similarity 0.86)
- Plug-and-Play image restoration with Stochastic deNOising REgularization (ICML 2024 · similarity 0.86)
- Stochastic Deep Restoration Priors for Imaging Inverse Problems (ICML 2025 · similarity 0.86)
- Exact Posterior Score Estimation for Solving Linear Inverse Problems (NeurIPS 2026 · similarity 0.86)
- Provably Robust Score-Based Diffusion Posterior Sampling for Plug-and-Play Image Reconstruction (NeurIPS 2024 · similarity 0.86)
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.
