Provably Contractive and High-Quality Denoisers for Convergent Restoration

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.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.