mlsanityData to 7 Oct 2026

CLIMB-flow: Coupled Linear Inverse posterior sampling via Multiscale-Based flow

arXiv 2609.33834 ↗First posted 27 Sep 2026cs.CV cs.LGcited by 0

On the map: Diffusion models → Inverse problems and image restoration

Abstract (arXiv)

Diffusion models are now widely used in Bayesian inverse problems in imaging as priors, where latent diffusion models are often used for larger scale problems to keep the computational complexity and model-size manageable. Unfortunately, the auto-encoder based compression results in loss of spatial detail. In addition, the optimization is converted to a non-linear problem. In this paper, we introduce a posterior sampling algorithm customized for the pyramidal/cascaded architecture, which relies on a coarse to fine hierarchical strategy to generate images in the pixel domain. We present CLIMB-Flow which alternates between three steps: an end-point estimation from the current coarse and noisy image, data-consistent update of the clean image, and re-noising it back to the level the network expects. Together these steps sample the posterior at that scale using an approximate Gibbs sampling from two conditional distributions. Experiments on ImageNet, CelebA, AFHQ and fastMRI span inpainting, deblurring, super-resolution and accelerated MRI, with PSNR gains of 1.37-7.66 dB over the strongest competing method on CelebA and pixel-domain reconstruction up to 512x512.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Inverse problems and image restoration, one of 14 directions in Diffusion models. Builds on 28 of its 33 references that are in the map. First posted on arXiv 27 Sep 2026.

Builds on

28 of 33 references.

Closest ancestors · 11

Same direction, newest first

  1. 2026Noise-Adaptive Diffusion Sampling for Inverse Problems Without Task-Specific Tuning18 Apr
  2. 2025Measurement Score-Based Diffusion Model17 May
  3. 2024PnP-Flow: Plug-and-Play Image Restoration with Flow Matching3 Oct
  4. 2024A Survey on Diffusion Models for Inverse Problems30 Sep
  5. 2024Improving Diffusion Inverse Problem Solving with Decoupled Noise Annealing1 Jul
  6. 2023Solving Inverse Problems with Latent Diffusion Models via Hard Data Consistency16 Jul
  7. 2023Solving Linear Inverse Problems Provably via Posterior Sampling with Latent Diffusion Models2 Jul
  8. 2023Denoising Diffusion Models for Plug-and-Play Image Restoration15 May
  9. 2022Zero-Shot Image Restoration Using Denoising Diffusion Null-Space Model1 Dec
  10. 2022Diffusion Posterior Sampling for General Noisy Inverse Problems29 Sep
  11. 2022Denoising Diffusion Restoration Models27 Jan

Other references · 17

  1. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  2. 2022Scalable Diffusion Models with Transformerscited by 5,931
  3. 2022Flow Matching for Generative Modelingcited by 5,426
  4. 2022Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flowcited by 3,550
  5. 2021Cascaded Diffusion Models for High Fidelity Image Generationcited by 1,155
  6. 2022Building Normalizing Flows with Stochastic Interpolantscited by 964
  7. 2025FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Spacecited by 960
  8. 2021Solving Inverse Problems in Medical Imaging with Score-Based Generative Modelscited by 514
  9. 2018fastMRI: An Open Dataset and Benchmarks for Accelerated MRIcited by 464
  10. 2024Pyramidal Flow Matching for Efficient Video Generative Modelingcited by 354
  11. 2022Wavelet Diffusion Models are fast and scalable Image Generatorscited by 116
  12. 2024D-Flow: Differentiating through Flows for Controlled Generationcited by 115
5 more
  1. 2025PixelFlow: Pixel-Space Generative Models with Flowcited by 91
  2. 2023Training-free Linear Image Inverses via Flowscited by 70
  3. 2024Flow Priors for Linear Inverse Problems via Iterative Corrupted Trajectory Matchingcited by 50
  4. 2025Flower: A Flow-Matching Solver for Inverse Problemscited by 23
  5. 2025Latent Diffusion Models with Masked AutoEncoderscited by 11

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026SNaP: One-Step Posterior Sampling for Noisy Inverse Problems
  2. 2026A Posterior-Dynamics Framework for Imaging Inverse Problems with Pretrained Diffusion Priors
  3. 2024Posterior Sampling with Denoising Oracles via Tilted Transport
  4. 2026FlowSGS: Improving Flow Matching Priors for Inverse Imaging with Stochastic Interpolants
  5. 2024Divide-and-Conquer Posterior Sampling for Denoising Diffusion Priors
  6. 2026Annealed Langevin Posterior Sampling (ALPS): A Rapid Algorithm for Image Restoration with Multiscale Energy Models
  7. 2026ShuffleFlow: Scalable Posterior Inference for Bayesian Inverse Imaging
  8. 2024Amortized Posterior Sampling with Diffusion Prior Distillation