Pith. sign in

REVIEW 5 cited by

SITCOM: Step-wise Triple-Consistent Diffusion Sampling for Inverse Problems

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2410.04479 v2 pith:3YGSJGZL submitted 2024-10-06 eess.IV cs.CVcs.LG

Ismail Alkhouri , Shijun Liang , Cheng-Han Huang , Jimmy Dai , Qing Qu , Saiprasad Ravishankar , Rongrong Wang This is my paper · ORCID
classification eess.IVcs.CVcs.LG
keywords samplingdiffusionstepsconditionsconsistencysitcomstep-wisedistribution
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Diffusion models (DMs) are a class of generative models that allow sampling from a distribution learned over a training set. When applied to solving inverse problems, the reverse sampling steps are modified to approximately sample from a measurement-conditioned distribution. However, these modifications may be unsuitable for certain settings (e.g., presence of measurement noise) and non-linear tasks, as they often struggle to correct errors from earlier steps and generally require a large number of optimization and/or sampling steps. To address these challenges, we state three conditions for achieving measurement-consistent diffusion trajectories. Building on these conditions, we propose a new optimization-based sampling method that not only enforces standard data manifold measurement consistency and forward diffusion consistency, as seen in previous studies, but also incorporates our proposed step-wise and network-regularized backward diffusion consistency that maintains a diffusion trajectory by optimizing over the input of the pre-trained model at every sampling step. By enforcing these conditions (implicitly or explicitly), our sampler requires significantly fewer reverse steps. Therefore, we refer to our method as Step-wise Triple-Consistent Sampling (SITCOM). Compared to SOTA baselines, our experiments across several linear and non-linear tasks (with natural and medical images) demonstrate that SITCOM achieves competitive or superior results in terms of standard similarity metrics and run-time.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Diffusion-based mass map reconstruction from weak lensing data

    astro-ph.CO 2025-02 conditional novelty 6.0 of 10

    A single unconditioned diffusion model plus a rescaled Diffusion Posterior Sampling step reconstructs weak lensing mass maps whose power spectra and non-Gaussian statistics match the simulations.

  2. DICT: Data Injection and Contrastive Trajectory Refinement for Conditional Image Generation with Diffusion Models

    cs.CV 2026-07 conditional novelty 5.5 of 10

    Noise-perturbed condition injection plus contrastive trajectory refinement improves training-free conditional diffusion sampling across style transfer, super-resolution and deblurring.

  3. Enhancing Diffusion Model Stability for Image Restoration via Gradient Management

    cs.CV 2025-07 conditional novelty 5.0 of 10

    SPGD combines a progressive likelihood warm-up with adaptive directional momentum to reduce gradient conflicts and fluctuations in diffusion-based image restoration, improving metrics over existing baselines.

  4. Local MAP Sampling for Diffusion Models

    cs.GR 2025-10 conditional novelty 4.0 of 10

    LMAPS frames reverse-diffusion inverse-problem solving as repeated local MAP estimation, unifying existing optimization-based solvers, and achieves strong PSNR gains on tasks like motion deblurring, JPEG restoration, ...

  5. Improving Decoupled Posterior Sampling for Inverse Problems using Data Consistency Constraint

    cs.LG 2024-12 conditional novelty 4.0 of 10

    Guided Decoupled Posterior Sampling (GDPS) adds a gradient step on the measurement mismatch ||y - A(x_t)||^2 during the reverse process, improving reconstruction accuracy over DAPS, SITCOM, Resample, and DPS.

Pith tools