A blind image denoising framework based on an infinite directional lower semi-frame (DLSF) is introduced for additive white Gaussian noise. The method estimates noise variance directly in the DLSF domain using joint covariance of four directional difference channels, then applies channel‑wise Wiener‑type shrinkage and canonical‑dual synthesis with data‑consistent iterative reconstruction. Experiments on three standard grayscale images show a mean relative noise‑estimation error of 3.28 % and average PSNR gains of 7.45 dB, improving to 8.31 dB at 30/255 noise.
arXiv:2510.04382v3 Announce Type: replace-cross Abstract: Even though more than 30 years have passed since the seminal Rudin--Osher--Fatemi (ROF) paper on total variation (TV) denoising, it remains r...
arXiv:2608.29227v1 Announce Type: new Abstract: In this work we propose a novel non-linear diffusion filtering approach for images based on their channel representation. To derive the diffusion updat...
The paper proposes a new covariance model for Denoising Diffusion Probabilistic Models (DDPMs) that captures non‑diagonal correlations and the power‑law frequency spectrum of natural images. Using a Kronecker‑factored DCT (K‑DCT) decomposition, the authors reduce computational complexity from quadratic to log‑linear, enabling efficient sampling with few steps. Experiments on CIFAR‑10, Celeb‑A, ImageNet, and LSUN demonstrate improved FID and likelihoods over previous state‑of‑the‑art samplers.
arXiv:2609.00036v1 Announce Type: new Abstract: The total scaled-gradient variation (TSGV) regularizer, derived from sparse modeling of piecewise-linear structures, has been shown to preserve edges a...
The paper presents convergence guarantees for Plug-and-Play (PnP) image restoration algorithms that use annealed noise levels, covering both deterministic and stochastic methods. It identifies explicit nonconvex objectives linked to the final denoising level and proves that iterates become asymptotically stationary with respect to these objectives, without requiring a specific noise decay schedule. The authors validate their theory experimentally on tasks such as inpainting, super‑resolution, demosaicing, and tomography.
MG-SpaIR is a training-data-free framework for restoring a clean image from a single observation corrupted by a mixture of blur, downsampling, noise, and missing pixels. Building on implicit neural representations (INRs), we introduce a multi-grade coarse-to-fine residual hierarchy that progressively refines the reconstruction across resolution grades, improving representational fidelity and mitigating spectral limitations.
arXiv:2609.00036v2 Announce Type: replace Abstract: The total scaled-gradient variation (TSGV) regularizer, derived from sparse modeling of piecewise-linear structures, has been shown to preserve edg...
The paper presents an unsupervised autoencoder that uses a Cohen-Daubechies-Feauveau (CDF 97) wavelet transform in its latent space to denoise neutron imaging data from inertial confinement fusion experiments. The method targets mixed Gaussian‑Poisson noise, preserving fine details and edges that are crucial for image reconstruction. Benchmarks on simulated and experimental NIF datasets show lower reconstruction error and better edge preservation than conventional filtering techniques such as BM3D.
arXiv:2609.23268v1 Announce Type: new Abstract: Blind image deconvolution (BID) is a prominent research topic in the field of imaging sciences, given its significant practical applications. Most exis...
SAR-FAH is a Frequency‑Adaptive Hybrid network that uses Neural Ordinary Differential Equations (NODEs) to despeckle Synthetic Aperture Radar (SAR) images. It separates homogeneous and heterogeneous regions in the frequency domain via wavelet transform, then applies a NODE‑based module to low‑frequency sub‑bands for smooth denoising and an enhanced U‑Net with deformable convolutions to high‑frequency sub‑bands for edge and texture preservation. Experiments on synthetic and real SAR data show that SAR‑FAH outperforms current state‑of‑the‑art despeckling methods both quantitatively and qualitatively.
arXiv:2609.07012v1 Announce Type: cross Abstract: Pushbroom satellite imaging couples limited spatial resolution with platform attitude instability. Platform jitter produces spatially varying motion...
UGDiff introduces an uncertainty-guided diffusion paradigm for single-image super-resolution, aiming to improve the perception‑distortion trade‑off. The method estimates reconstruction uncertainty of latent features from a high‑fidelity image and uses this uncertainty, along with diffusion sampler posterior variance, to selectively restore high‑frequency details in uncertain regions while preserving fidelity elsewhere. Experiments show that UGDiff outperforms state‑of‑the‑art diffusion‑based SR methods.