Research map / Image generation / Fast diffusion sampling
FAST‑DIPS: Adjoint‑Free Analytic Steps and Hard‑Constrained Likelihood Correction for Diffusion‑Prior Inverse Problems
Minwoo Kim, Seunghyeok Shin, Hongki Lim
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 hard-constraint projection (ADMM) instead of unsplit penalized QDP at matched budget (ablation) | FAST-DIPS · Ablation (Gaussian blur, latent HDR) | reconstruction quality | Improved |
| use forward-difference step size alpha_FD instead of analytic alpha* (ablation) | FAST-DIPS · Gaussian blur (pixel) | reconstruction quality | No clear effect |
| use forward-difference step size alpha_FD instead of JVP-based alpha* (ablation) | FAST-DIPS · HDR (latent) | reconstruction quality | Hurt |
| analytic step size instead of tuned constant step (ablation) | FAST-DIPS · HDR (latent) | reconstruction quality | Improved |
| FAST-DIPS vs DAPS run-time | FAST-DIPS · FFHQ Gaussian deblurring | run-time (s): 50.400 -> 2.612 | Improved |
| FAST-DIPS vs DAPS run-time | FAST-DIPS · FFHQ phase retrieval | run-time (s): 122.100 -> 10.354 | Improved |
| FAST-DIPS vs SITCOM quality | FAST-DIPS · FFHQ nonlinear deblur (pixel) | PSNR: 29.770 -> 27.818 | Hurt |
| hybrid pixel-then-latent correction schedule vs LatentDAPS | FAST-DIPS latent · FFHQ Gaussian deblurring (latent) | run-time (s): 93.313 -> 46.307 | Improved |
| increase correction steps per noise level (ablation) | FAST-DIPS · four tasks | PSNR/LPIPS | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- SITCOM — SITCOM: Step-wise Triple-Consistent Diffusion Sampling For Inverse Problems (ICML 2025) · better on 10 of 14 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- A Variational Perspective on Solving Inverse Problems with Diffusion Models (ICLR 2024 · similarity 0.90)
- Improving Diffusion-based Inverse Algorithms under Few-Step Constraint via Linear Extrapolation (NeurIPS 2025 · similarity 0.90)
- Unleashing the Denoising Capability of Diffusion Prior for Solving Inverse Problems (NeurIPS 2024 · similarity 0.90)
- Improving Diffusion Inverse Problem Solving with Decoupled Noise Annealing (CVPR 2025 · similarity 0.89)
- Divide-and-Conquer Posterior Sampling for Denoising Diffusion priors (NeurIPS 2024 · similarity 0.89)
- DMPlug: A Plug-in Method for Solving Inverse Problems with Diffusion Models (NeurIPS 2024 · similarity 0.89)
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.
