#inverse-problems News & Analysis

8 articles tagged with #inverse-problems. AI-curated summaries with sentiment analysis and key takeaways from 50+ sources.

8 articles

AIBullisharXiv – CS AI · 3d ago7/10

🧠

PnP-CM: Consistency Models as Plug-and-Play Priors for Inverse Problems

Researchers introduce PnP-CM, a new method that reformulates consistency models as proximal operators within plug-and-play frameworks for solving inverse problems. The approach achieves high-quality image reconstructions with minimal neural function evaluations (4 NFEs), demonstrating practical efficiency gains over existing consistency model solvers and marking the first application of CMs to MRI data.

AINeutralarXiv – CS AI · Mar 116/10

🧠

Latent Generative Models with Tunable Complexity for Compressed Sensing and other Inverse Problems

Researchers developed tunable-complexity priors for generative models (diffusion models, normalizing flows, and variational autoencoders) that can dynamically adjust complexity based on the specific inverse problem. The approach uses nested dropout and demonstrates superior performance across compressed sensing, inpainting, denoising, and phase retrieval tasks compared to fixed-complexity baselines.

AIBullisharXiv – CS AI · Mar 36/1012

🧠

Efficient Flow Matching for Sparse-View CT Reconstruction

Researchers developed FMCT/EFMCT, a new Flow Matching-based framework for CT medical imaging reconstruction that significantly improves computational efficiency over existing diffusion models. The method uses deterministic ordinary differential equations and velocity field reuse to reduce neural network evaluations while maintaining reconstruction quality.

AIBullisharXiv – CS AI · Mar 36/108

🧠

FAST-DIPS: Adjoint-Free Analytic Steps and Hard-Constrained Likelihood Correction for Diffusion-Prior Inverse Problems

Researchers propose FAST-DIPS, a new training-free diffusion prior method for solving inverse problems that achieves up to 19.5x speedup while maintaining competitive image quality metrics. The method replaces computationally expensive inner optimization loops with closed-form projections and analytic step sizes, significantly reducing the number of required denoiser evaluations.

AIBullisharXiv – CS AI · Mar 36/103

🧠

EquiReg: Equivariance Regularized Diffusion for Inverse Problems

Researchers propose EquiReg, a new framework that improves diffusion models for inverse problems like image restoration by keeping sampling trajectories on the data manifold. The method uses equivariance regularization to guide sampling toward symmetry-preserving regions, enabling high-quality reconstructions with fewer sampling steps.

AIBullisharXiv – CS AI · Feb 275/107

🧠

Learning to reconstruct from saturated data: audio declipping and high-dynamic range imaging

Researchers have developed a self-supervised learning method that can reconstruct audio and images from clipped/saturated measurements without requiring ground truth training data. The approach extends self-supervised learning to non-linear inverse problems and performs nearly as well as fully supervised methods while using only clipped measurements for training.

AINeutralarXiv – CS AI · Mar 34/103

🧠

DAWN-FM: Data-Aware and Noise-Informed Flow Matching for Solving Inverse Problems

Researchers introduce DAWN-FM, a new AI method using Flow Matching to solve inverse problems in fields like medical imaging and signal processing. The approach incorporates data and noise embedding to provide robust solutions even with incomplete or noisy observations, outperforming pretrained diffusion models in highly ill-posed scenarios.

AINeutralarXiv – CS AI · Mar 34/105

🧠

Solving Inverse PDE Problems using Minimization Methods and AI

Researchers published a study comparing traditional numerical methods with Physics-Informed Neural Networks (PINNs) for solving direct and inverse problems in differential equations. The work demonstrates that PINNs can effectively estimate solutions at competitive computational costs for complex systems like the Porous Medium Equation.