The paper introduces a novel nonlinear diffusion scheme for image denoising, derived from a linear diffusion process applied in a value space tailored to specific application domains such as image compression, still-image acquisition, and medical imaging. It argues that this application-driven linear diffusion in the transformed space outperforms existing nonlinear diffusion techniques.
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 introduces a tensor‑based functional for targeted image enhancement and denoising, incorporating application‑dependent and contextual information through explicit regularization. It establishes existence of a minimizer and discusses tensor symmetry constraints, convexity, and geometric interpretation. The framework demonstrates strong performance in nonlinear scenarios like gamma correction and targeted value‑range filtering, achieving results comparable to state‑of‑the‑art PDE‑based methods.
arXiv:2505. 16733v3 Announce Type: replace Abstract: This paper proposes to perform image restoration through a state-dependent mean-reverting forward diffusion (FoD) process.
arXiv:2608.22302v1 Announce Type: new Abstract: The case when a partial differential equation (PDE) can be considered as an Euler-Lagrange (E-L) equation of an energy functional, consisting of a data...
Image acquisition with a camera involves several degradations due to the optical system, sensor, or low-level processing steps. We address blind deblurring in professional photography: we aim to inver...
arXiv:2606. 04299v1 Announce Type: cross Abstract: We consider the problem of generating images whose internal structure -- defined by the distribution of patches across multiple scales -- matches that of a single reference image.
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.
arXiv:2605.09477v2 Announce Type: replace-cross Abstract: Methods based on diffusion models (DMs) for solving inverse problems (IPs) have recently achieved remarkable performance. However, DM-based m...
The paper introduces SuperSharpen, a diffusion-based method for blind deblurring in professional photography that can invert unknown isotropic blur without knowing the degradation kernel. It offers explicit control over restoration strength via a blur measure and compares two conditioning strategies: a ControlNet-style adapter on a frozen backbone and full finetuning of the diffusion prior. Experiments on synthetic and real-world blur show that finetuning yields higher fidelity with fewer hallucinated details, improving perceptual quality and controllable restoration strength.
Pixel‑Space Diffusion via Observation Operators introduces a new framework for pixel‑space diffusion models that addresses a scale‑time mismatch in existing methods. By replacing fixed full‑image supervision with a time‑indexed observation trajectory that progresses from coarse structures to the full image, the model aligns supervision with the natural recovery order of image details. The approach employs Gaussian‑Lanczos operators and a GL‑CoDA decoder to refine features progressively, resulting in faster convergence and higher generation quality, achieving an FID of 1.52 on ImageNet‑256.
The paper introduces a perceptually regularized diffusion framework for image super‑resolution, adding perceptual‑loss based regularization to the standard diffusion training objective. This approach incorporates prior knowledge to improve training convergence and encourages the recovery of meaningful image features. Experiments on benchmark datasets show enhanced perceptual quality while maintaining competitive distortion metrics.
The paper introduces LA-VDM, a landmark‑constrained algorithm that speeds up Vector Diffusion Maps (VDM) by employing a two‑stage normalization to handle nonuniform sampling in both data and landmark sets. It demonstrates that, under a manifold model with a frame bundle structure, LA‑VDM can accurately recover parallel transport from a point cloud and asymptotically converges to the connection Laplacian. Experiments on simulated data and a nonlocal image denoising application confirm the method’s performance and accuracy.