paper-with-me

Papers

Deep Unfolding with Normalizing Flow Priors for Inverse Problems

2021-07-06 · Xinyi Wei, Hans van Gorp, Lizeth Gonzalez Carabarin, Daniel Freedman, Yonina C. Eldar, Ruud J. G. van Sloun

Many application domains, spanning from computational photography to medical imaging, require recovery of high-fidelity images from noisy, incomplete or partial/compressed measurements. State of the art methods for solving these inverse problems combine deep learning with iterative model-based solvers, a concept known as deep algorithm unfolding. By combining a-priori knowledge of the forward measurement model with learned (proximal) mappings based on deep networks, these methods yield solutions that are both physically feasible (data-consistent) and perceptually plausible. However, current proximal mappings only implicitly learn such image priors. In this paper, we propose to make these image priors fully explicit by embedding deep generative models in the form of normalizing flows within the unfolded proximal gradient algorithm. We demonstrate that the proposed method outperforms competitive baselines on various image recovery tasks, spanning from image denoising to inpainting and deblurring.

📄 PDF Abstract BibTeX arXiv:2107.02848

Code (0)

등록된 구현이 없습니다.

Tasks

DeblurringDenoisingImage Denoising

Methods 이 논문이 사용한 방법론

Inpainting Train a convolutional neural network to generate the contents of an arbitrary image region conditioned on its surroundings.
Normalizing Flows Normalizing Flows are a method for constructing complex distributions by transforming a probability density through a series of invertible mappings. By repeatedly applying…

Similar Papers 제목 키워드 기반

On the Robustness of Normalizing Flows for Inverse Problems in Imaging

2022-12-08 · ICCV 2023 1 · Seongmin Hong, Inbum Park, Se Young Chun

Conditional normalizing flows can generate diverse image samples for solving inverse problems. Most normalizing flows for inverse problems in imaging employ the conditional affine coupling layer that can generate diverse…

Image EnhancementLow-Light Image EnhancementSuper-Resolution

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

2026-03-07 · Sean Gunn, Jorio Cocola, Oliver De Candido, Vaggos Chatziafratis 외 arxiv

Generative models have emerged as powerful priors for solving inverse problems. These models typically represent a class of natural signals using a single fixed complexity or dimensionality. This can be limiting: dependi…

Proximal Residual Flows for Bayesian Inverse Problems

2022-11-30 · Johannes Hertrich

Normalizing flows are a powerful tool for generative modelling, density estimation and posterior reconstruction in Bayesian inverse problems. In this paper, we introduce proximal residual flows, a new architecture of nor…

Density Estimation

Stochastic Normalizing Flows for Inverse Problems: a Markov Chains Viewpoint

2021-09-23 · Paul Hagemann, Johannes Hertrich, Gabriele Steidl

To overcome topological constraints and improve the expressiveness of normalizing flow architectures, Wu, K\"ohler and No\'e introduced stochastic normalizing flows which combine deterministic, learnable flow transformat…

NF-ULA: Langevin Monte Carlo with Normalizing Flow Prior for Imaging Inverse Problems

2023-04-17 · Ziruo Cai, Junqi Tang, Subhadip Mukherjee, Jinglai Li 외

Bayesian methods for solving inverse problems are a powerful alternative to classical methods since the Bayesian approach offers the ability to quantify the uncertainty in the solution. In recent years, data-driven techn…

Bayesian InferenceComputed Tomography (CT)CT ReconstructionDeblurring+3