Efficient diffusion posterior sampling for noisy inverse problems

DOI10.1137/24M1688321MaRDI QIDQ6960177zbMATH OpenFDO

Authors Ji Li, Chao Wang

Publication date 14 July 2025

Published in SIAM Journal on Imaging Sciences (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1137/24M1688321

zbMATH Keywords

diffusion generative modelinverse problemsposterior sampling

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Image processing (compression, reconstruction, etc.) in information and communication theory (94A08) Signal theory (characterization, reconstruction, filtering, etc.) (94A12) Sampling theory in information and communication theory (94A20)

Cites work

• rm K-SVD: An Algorithm for Designing Overcomplete Dictionaries for Sparse Representation
• Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising
• Compressed sensing
• Data-driven multi-scale non-local wavelet frame construction and image recovery
• Image restoration: total variation, wavelet frames, and beyond
• Nonlinear total variation based noise removal algorithms
• Provably Convergent Plug-and-Play Quasi-Newton Methods
• Theoretical foundations and numerical methods for sparse recovery. Papers based on the presentations of the summer school ``Theoretical foundations and numerical methods for sparse recovery, Vienna, Austria, August 31 -- September 4, 2009.
• Wavelet frame based blind image inpainting

Cited in

(2)

• Two-view CBCT reconstruction via preconditioned gradient descent with plug-and-play diffusion anatomical prior
• A two-order time-fractional diffusion coupled system for image denoising based on the \(H^{- 1}\) norm

This page was built for publication: Efficient diffusion posterior sampling for noisy inverse problems

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6960177)