The paper introduces denoiser networks that are provably contractive, meaning their global Lipschitz constant is less than one. By combining proximal layers from unfolding techniques with Lipschitz‑controlled convolutional refinements, the authors ensure that small input perturbations produce at most equally small output changes, unlike many strong unconstrained baselines. The proposed denoisers achieve high restoration quality on image denoising tasks, close to that of powerful unconstrained models, and when used as priors in Plug‑and‑Play frameworks, they guarantee convergence and strong empirical performance.
arXiv:2608. 09482v1 Announce Type: cross Abstract: All-in-one image restoration is a unified low-level vision task that aims to effectively recover high-quality images from inputs degraded by various types and levels of corruption using a single model.
arXiv:2607. 14894v1 Announce Type: cross Abstract: Plug-and-play proximal gradient descent (PnP-PGD) enables flexible image reconstruction by using denoisers as implicit priors.
arXiv:2504.10201v3 Announce Type: replace Abstract: In this paper, we introduce a synthetic image generator relying on a few simple principles, specifically focusing on geometric modeling, textures,...
arXiv:2406. 07435v2 Announce Type: replace-cross Abstract: Image restoration networks are usually comprised of an encoder and a decoder, responsible for aggregating image content from noisy, distorted data and to restore clean, undistorted images, respectively.
arXiv:2609.14690v1 Announce Type: new Abstract: Onboard satellites must restore a channel-degraded image on a few watts, using neuromorphic accelerators (e.g., BrainChip Akida, Intel Loihi-2) that su...
arXiv:2608. 04944v1 Announce Type: cross Abstract: We propose a deep learning framework for image restoration from images degraded by both multiplicative Gamma noise and blur.
arXiv:2609.13791v1 Announce Type: new Abstract: Recognition pipelines typically adopt a restore-then-recognize workflow, yet decades of experience show that generating visually pleasing images seldom...
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:2606. 19802v1 Announce Type: new Abstract: Image restoration faces a fundamental tradeoff: methods that minimize error produce blurry reconstructions, while those that maximize perceptual quality yield sharp but less faithful images.
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.
The paper introduces SANA‑SR, an efficient one‑step diffusion restoration framework for real‑world image super‑resolution. It uses a deep compression autoencoder to reduce latent tokens by a 32× ratio, preserving essential structures and textures, and applies a linear‑attention DiT with LoRA fine‑tuning for linear‑complexity token mixing. Experiments show competitive or superior performance on benchmark datasets, and the pruned model runs in 0.019 s with 407.95 G MACs and 344 M parameters, indicating strong potential for mobile deployment.
The paper introduces Sparsity-Adaptive Sharpness-Aware Minimization (SA‑SAM), a method that adjusts the perturbation radius in sharpness-aware training to remain consistent as model sparsity increases. It also evaluates a Magnitude‑Weighted Hessian (MWH) importance metric derived from second‑order analysis. Experiments on CIFAR‑10‑C, CIFAR‑100‑C, and ImageNet‑100‑C show that SA‑SAM improves corruption robustness at 80–90% sparsity while maintaining clean accuracy, and the study reports inference throughput at deployment‑relevant sparsity levels.