Dynamic resolution priors enable faster diffusion-based image restoration by operating in lower-dimensional subspaces, with adapted methods outperforming prior DM approaches on most tasks.
hub
De- coupled data consistency with diffusion purification for image restoration
13 Pith papers cite this work. Polarity classification is still indexing.
13
Pith papers citing it
hub tools
citation-role summary
background 2
citation-polarity summary
roles
background 2polarities
background 2representative citing papers
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.
Introduces the Invariant Contamination Ratio (ICR), a Fisher-based metric, to evaluate how diffusion models balance invariant representations with residual variation and to detect the onset of memorization during training.
PPM derives a tractable gradient for exact KL optimization in diffusion variational inversion to achieve unbiased posterior matching without heuristic approximations.
ForcingDAS is a diffusion-based data assimilation framework that learns joint-trajectory priors to unify filtering and smoothing while reducing error accumulation on non-Markovian observations.
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.
SOCS derives per-step closed-form control signals from stochastic optimal control to steer diffusion sampling trajectories toward measurements while preserving the generative prior.
Numerical benchmarks indicate generative regularizers deliver strong reconstructions in some imaging inverse problem settings but can be unstable or problematic under imperfect conditions compared to variational methods.
Diffusion-based inverse problem solvers are made robust to outliers by combining explicit noise estimation with a Huber-loss IRLS objective solved via conjugate gradient.
DAPS++ decouples diffusion initialization from likelihood-only MCMC refinement, cutting neural function evaluations by about 90% while matching or improving image restoration quality.
A dual ascent optimization framework is introduced for MAP estimation with diffusion priors, claimed to outperform prior methods on image restoration in quality, noise robustness, speed, and data fidelity.
High-dimensional embedding prior improves diffusion-based k-space MRI reconstruction under noise by augmenting representation space.
A survey organizing AI methods for inverse PDE problems into inverse problems, inverse design, and control categories, covering applications and future challenges like physics-informed models and uncertainty quantification.
citing papers explorer
-
Image Restoration via Diffusion Models with Dynamic Resolution
Dynamic resolution priors enable faster diffusion-based image restoration by operating in lower-dimensional subspaces, with adapted methods outperforming prior DM approaches on most tasks.
-
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.
-
Evaluating the Representation Space of Diffusion Models via Self-Supervised Principles
Introduces the Invariant Contamination Ratio (ICR), a Fisher-based metric, to evaluate how diffusion models balance invariant representations with residual variation and to detect the onset of memorization during training.
-
Unbiased Diffusion Variational Inversion via Principled Posterior Matching
PPM derives a tractable gradient for exact KL optimization in diffusion variational inversion to achieve unbiased posterior matching without heuristic approximations.
-
ForcingDAS: Unified and Robust Data Assimilation via Diffusion Forcing
ForcingDAS is a diffusion-based data assimilation framework that learns joint-trajectory priors to unify filtering and smoothing while reducing error accumulation on non-Markovian observations.
-
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.
-
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.
-
A Stability Benchmark of Generative Regularizers for Inverse Problems
Numerical benchmarks indicate generative regularizers deliver strong reconstructions in some imaging inverse problem settings but can be unstable or problematic under imperfect conditions compared to variational methods.
-
Outlier-Robust Diffusion Solvers for Inverse Problems
Diffusion-based inverse problem solvers are made robust to outliers by combining explicit noise estimation with a Huber-loss IRLS objective solved via conjugate gradient.
-
DAPS++: Rethinking Diffusion Inverse Problems with Decoupled Posterior Annealing
DAPS++ decouples diffusion initialization from likelihood-only MCMC refinement, cutting neural function evaluations by about 90% while matching or improving image restoration quality.
-
Dual Ascent Diffusion for Inverse Problems
A dual ascent optimization framework is introduced for MAP estimation with diffusion priors, claimed to outperform prior methods on image restoration in quality, noise robustness, speed, and data fidelity.
-
High-dimensional Embedding Prior for Noisy K-space Domain MRIReconstruction
High-dimensional embedding prior improves diffusion-based k-space MRI reconstruction under noise by augmenting representation space.
-
Harnessing AI for Inverse Partial Differential Equation Problems: Past, Present, and Prospects
A survey organizing AI methods for inverse PDE problems into inverse problems, inverse design, and control categories, covering applications and future challenges like physics-informed models and uncertainty quantification.