REVIEW 16 cited by
Tweedie Moment Projected Diffusions For Inverse Problems
Not yet reviewed by Pith; the record is open.
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
Tweedie Moment Projected Diffusions For Inverse Problems
read the original abstract
Diffusion generative models unlock new possibilities for inverse problems as they allow for the incorporation of strong empirical priors in scientific inference. Recently, diffusion models are repurposed for solving inverse problems using Gaussian approximations to conditional densities of the reverse process via Tweedie's formula to parameterise the mean, complemented with various heuristics. To address various challenges arising from these approximations, we leverage higher order information using Tweedie's formula and obtain a statistically principled approximation. We further provide a theoretical guarantee specifically for posterior sampling which can lead to a better theoretical understanding of diffusion-based conditional sampling. Finally, we illustrate the empirical effectiveness of our approach for general linear inverse problems on toy synthetic examples as well as image restoration. We show that our method (i) removes any time-dependent step-size hyperparameters required by earlier methods, (ii) brings stability and better sample quality across multiple noise levels, (iii) is the only method that works in a stable way with variance exploding (VE) forward processes as opposed to earlier works.
Forward citations
Cited by 16 Pith papers
-
Divergence is Uncertainty: A Closed-Form Posterior Covariance for Flow Matching
In flow matching, the uncertainty of the clean data given the current state is exactly the divergence of the velocity field (up to a known scalar).
-
Divergence is Uncertainty: A Closed-Form Posterior Covariance for Flow Matching
Derives closed-form posterior covariance for flow matching from divergence of velocity field, enabling post-hoc uncertainty on pre-trained models including one-step generators.
-
Reflection Separation from a Single Image via Joint Latent Diffusion
A joint latent diffusion model with cross-layer self-attention and disjoint sampling separates reflection and transmission layers from single images more effectively than prior methods on real-world benchmarks.
-
Proximal-Based Generative Modeling for Bayesian Inverse Problems
PGM framework links diffusion to proximal regularization for closed-form Moreau-score sampling in Bayesian inverse problems, learned only from prior samples.
-
Proximal-Based Generative Modeling for Bayesian Inverse Problems
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.
-
Covariance-aware sampling for Diffusion Models
A covariance-aware extension of DDIM sampling for pixel-space diffusion models that uses Tweedie's formula and Fourier decomposition to model reverse-process covariance and improves sample quality at low NFE.
-
Divergence is Uncertainty: A Closed-Form Posterior Covariance for Flow Matching
An exact closed-form posterior covariance for flow matching is derived from the divergence of the velocity field and is computable on any pre-trained model.
-
Sample-efficient evidence estimation of score based priors for model selection
DiME estimates model evidence for diffusion priors by integrating time-marginals from posterior sampling, enabling efficient prior selection and misfit diagnosis in ill-posed inverse problems.
-
Efficient Zero-Shot Inpainting with Decoupled Diffusion Guidance
A new decoupled diffusion guidance method enables efficient zero-shot inpainting by avoiding backpropagation through the denoiser while maintaining observation consistency and quality.
-
Physics Matters in PnP: Recovery Guarantees with the MMSE and NN Denoisers
PnP-FBS with MMSE denoisers recovers the true signal with explicit pointwise and Wasserstein error bounds, provided the denoiser's noise covariance is matched to the preconditioned observation noise.
-
Amortized Moment Matching for Visual Generation
Amortized Fréchet Distance uses neural nets to match conditional means and covariances, yielding stronger one-step visual generators than explicit FD-loss or multi-step teachers.
-
Optimizing Diffusion Priors in Image Reconstruction from a Single Observation
Combining diffusion priors as a product-of-experts and optimizing exponents via Bayesian evidence maximization enables prior tuning from one observation in inverse imaging problems.
-
Jacobian-Aware Posterior Sampling for Inverse Problems
AdaPS adaptively scales likelihood guidance in DDIM posterior sampling via agreement between two surrogates, improving LPIPS/PSNR trade-offs on image restoration tasks without task-specific tuning.
-
Integration Matters: Rollout-Based Training for Constrained Diffusion Models
Rollout-based fine-tuning with a learned adaptive guidance scaling yields near-zero constraint violations while preserving sample fidelity in constrained diffusion models.
-
Stochastic Optimal Control Sampling for Diffusion Inverse Problems
SOCS derives per-step closed-form control signals from stochastic optimal control to steer diffusion sampling trajectories toward measurements while preserving the generative prior.
-
Local MAP Sampling for Diffusion Models
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, ...
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.