Pith. sign in

REVIEW 17 cited by

Solving Inverse Problems with Latent Diffusion Models via Hard Data Consistency

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 2307.08123 v3 pith:TVUOUMKA submitted 2023-07-16 cs.CV

Bowen Song , Soo Min Kwon , Zecheng Zhang , Xinyu Hu , Qing Qu , Liyue Shen This is my paper
classification cs.CV
keywords diffusionmodelsdatainverseproblemslatentsolvingalgorithm
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Diffusion models have recently emerged as powerful generative priors for solving inverse problems. However, training diffusion models in the pixel space are both data-intensive and computationally demanding, which restricts their applicability as priors for high-dimensional real-world data such as medical images. Latent diffusion models, which operate in a much lower-dimensional space, offer a solution to these challenges. However, incorporating latent diffusion models to solve inverse problems remains a challenging problem due to the nonlinearity of the encoder and decoder. To address these issues, we propose \textit{ReSample}, an algorithm that can solve general inverse problems with pre-trained latent diffusion models. Our algorithm incorporates data consistency by solving an optimization problem during the reverse sampling process, a concept that we term as hard data consistency. Upon solving this optimization problem, we propose a novel resampling scheme to map the measurement-consistent sample back onto the noisy data manifold and theoretically demonstrate its benefits. Lastly, we apply our algorithm to solve a wide range of linear and nonlinear inverse problems in both natural and medical images, demonstrating that our approach outperforms existing state-of-the-art approaches, including those based on pixel-space diffusion models.

Discussion (0). Sign in to comment.

Forward citations

Cited by 17 Pith papers

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

  1. AgenticVBench: Can AI Agents Complete Real-World Post-Production Tasks?

    cs.CR 2026-05 unverdicted novelty 7.0 of 10

    AgenticVBench evaluates frontier VLMs on 100 real-world video post-production tasks across four families, with the best agent stack scoring just over 30% versus human experts.

  2. Proximal-Based Generative Modeling for Bayesian Inverse Problems

    math.OC 2026-05 unverdicted novelty 7.0 of 10

    PGM framework links diffusion to proximal regularization for closed-form Moreau-score sampling in Bayesian inverse problems, learned only from prior samples.

  3. Proximal-Based Generative Modeling for Bayesian Inverse Problems

    math.OC 2026-05 unverdicted novelty 7.0 of 10

    PGM replaces the intractable likelihood score in diffusion models with a closed-form Moreau score computed via proximal operators, enabling non-asymptotic sampling for inverse problems trained only on prior data.

  4. Discrete Langevin-Inspired Posterior Sampling

    cs.LG 2026-05 unverdicted novelty 7.0 of 10

    ΔLPS is a gradient-guided discrete posterior sampler for inverse problems that works with masked or uniform discrete diffusion priors and outperforms prior discrete methods on image restoration tasks.

  5. q3-MuPa: Quick, Quiet, Quantitative Multi-Parametric MRI using Physics-Informed Diffusion Models

    physics.med-ph 2025-12 unverdicted novelty 7.0 of 10

    A denoising diffusion model trained only on synthetic brain phantoms, with explicit physics-based data consistency, produces high-accuracy quantitative T1/T2/PD maps from fourfold-accelerated MuPa-ZTE acquisitions and...

  6. Blade: A Derivative-free Bayesian Inversion Method using Diffusion Priors

    cs.LG 2025-10 conditional novelty 7.0 of 10

    Blade produces well-calibrated derivative-free Bayesian posterior samples by combining split Gibbs sampling, ensemble statistical linearization, and diffusion priors.

  7. ART-VITON: Measurement-Guided Latent Diffusion for Artifact-Free Virtual Try-On

    cs.CV 2025-09 unverdicted novelty 7.0 of 10

    ART-VITON uses residual prior initialization and artifact-free measurement-guided sampling with data consistency, frequency correction, and periodic denoising to generate artifact-free virtual try-on images on VITON-H...

  8. Unbiased Diffusion Variational Inversion via Principled Posterior Matching

    cs.CV 2026-05 unverdicted novelty 6.0 of 10

    PPM derives a tractable gradient for exact KL optimization in diffusion variational inversion to achieve unbiased posterior matching without heuristic approximations.

  9. Longwang: Zero-Shot Global Spatiotemporal Precipitation Downscaling with a Latent Generative Prior

    physics.ao-ph 2026-05 unverdicted novelty 6.0 of 10

    Longwang enables zero-shot downscaling of global precipitation to daily 10 km resolution from monthly 100 km data by learning a context-conditioned latent generative prior and using posterior sampling with a physical ...

  10. Conditional Diffusion Posterior Alignment for Sparse-View CT Reconstruction

    eess.IV 2026-04 unverdicted novelty 6.0 of 10

    CDPA scales diffusion-based reconstruction to large 3D volumes by conditioning 2D models on initial 3D reconstructions plus data-consistency alignment, delivering state-of-the-art results on synthetic and real CBCT data.

  11. Solving Inverse Problems with Flow-based Models via Model Predictive Control

    eess.IV 2026-01 conditional novelty 6.0 of 10

    MPC-Flow applies model predictive control to guide pretrained flow models through inverse problems, with a single-step variant that avoids backpropagation and scales to 32B-parameter models on consumer hardware.

  12. NPN: Non-Linear Projections of the Null-Space for Imaging Inverse Problems

    cs.CV 2025-10 unverdicted novelty 6.0 of 10

    NPN introduces a neural-network-based regularization that promotes reconstructions lying in a low-dimensional projection of the sensing operator's null-space, with claimed theoretical guarantees and improved empirical...

  13. A novel method and dataset for depth-guided image deblurring from smartphone Lidar

    eess.IV 2025-09 conditional novelty 6.0 of 10

    Lidar depth-guided deblurring via a zero-shot diffusion method, evaluated on a new 45-scene dataset, achieves the best perceptual quality (LPIPS).

  14. Latent Space Diffusion for Topology Optimization

    cs.CE 2025-08 conditional novelty 6.0 of 10

    A VAE plus latent diffusion model with auxiliary physical losses generates topology-optimized structures with lower median compliance error than TopoDiff and TopoGAN on a 60k-sample 64x64 dataset.

  15. Provable diffusion-based posterior sampling for linear inverse problems via DDIM

    cs.LG 2026-07 reject novelty 5.0 of 10

    A SVD-based, coordinate-wise DDIM sampler is claimed to asymptotically sample from the posterior for noisy linear inverse problems, but the proof's posterior identification step does not follow from the stated updates.

  16. Towards Realistic Hand-Object Interaction with Gravity-Field Based Diffusion Bridge

    cs.CV 2025-09 conditional novelty 5.0 of 10

    A gravity-field and diffusion-based optimization refines hand-object contacts to reduce interpenetration and gaps while LLM text prompts guide contact regions.

  17. 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, ...

Pith tools