REVIEW 12 cited by
Solving Inverse Problems with Latent Diffusion Models via Hard Data Consistency
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
Solving Inverse Problems with Latent Diffusion Models via Hard Data Consistency
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.
Forward citations
Cited by 12 Pith papers
-
AgenticVBench: Can AI Agents Complete Real-World Post-Production Tasks?
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.
-
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.
-
Discrete Langevin-Inspired Posterior Sampling
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.
-
q3-MuPa: Quick, Quiet, Quantitative Multi-Parametric MRI using Physics-Informed Diffusion Models
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...
-
ART-VITON: Measurement-Guided Latent Diffusion for Artifact-Free Virtual Try-On
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...
-
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.
-
Longwang: Zero-Shot Global Spatiotemporal Precipitation Downscaling with a Latent Generative Prior
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 ...
-
Conditional Diffusion Posterior Alignment for Sparse-View CT Reconstruction
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.
-
Solving Inverse Problems with Flow-based Models via Model Predictive Control
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.
-
NPN: Non-Linear Projections of the Null-Space for Imaging Inverse Problems
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...
-
Provable diffusion-based posterior sampling for linear inverse problems via DDIM
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.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.