Trainable Nonexpansive Denoisers for Contractive Image Reconstruction

arXiv:2607.23347v1 Announce Type: cross Abstract: Trainable denoisers with Lipschitz control have become central to convergent image reconstruction. However, training neural networks that simultaneously offer strong denoising performance and global Lipschitz guarantees is challenging. Existing approaches enforce Lipschitz control only empirically, providing no guarantees beyond the training data. In this work, we show that by exploiting the action of permutations on the image lattice, we can constrain a neural architecture that is globally nonexpansive (Lipschitz bound leqslant 1). We integrate the proposed denoiser with forward imaging operators to develop a reconstruction mechanism that is provably contractive and therefore globally convergent. Experiments on standard inverse problems, such as superresolution and deblurring, demonstrate that our reconstruction performance is competitive with softly constrained baselines while providing Lipschitz guarantees.

Related

• Stabilizing Deep Reconstruction Operators with Contractive Anchoring
• Shared-kernel Wavelet Neural Networks for Poisson Image Reconstruction
• Pre-training Enables Extraordinary All-optical Image Denoising

Source: arXiv cs.CV | 2026-07-28