Trainable Nonexpansive Denoisers for Contractive Image Reconstruction

• URL: http://arxiv.org/abs/2607.23347v1
• Date: Sat, 25 Jul 2026 19:54:42 GMT
• Title: Trainable Nonexpansive Denoisers for Contractive Image Reconstruction
• Abstract summary: We show that by exploiting the action of permutations on the image lattice, we can constrain a neural architecture that is globally nonexpansive.<n>We integrate the proposed denoiser with forward imaging operators to develop a reconstruction mechanism that is provably contractive and therefore globally convergent.
• Score: 11.44690943348845
• License: http://creativecommons.org/licenses/by/4.0/
• 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 papers

• Lipschitz verification of neural networks through training [3.8708566551482537]
  We show that penalizing the trivial bound during training forces it to become tight, thereby effectively regularizing the true Lipschitz constant.<n>Our approach avoids the runtime complexity of advanced verification while achieving strong results.
  arXiv  Detail & Related papers  (2026-03-30T07:20:50Z)
• Provably Contractive and High-Quality Denoisers for Convergent Restoration [4.912983462300839]
  Existing convolutional and attention-based networks lack stability guarantees under minor shifts in input.<n>We develop provably contractive (global Lipschitz $ 1$) denoiser networks that considerably reduce this gap.<n>Our results show that enforcing strict Lipschitz control does not inherently degrade output quality.
  arXiv  Detail & Related papers  (2026-03-27T08:35:55Z)
• Representation Entanglement for Generation: Training Diffusion Transformers Is Much Easier Than You Think [63.25744258438214]
  REPA and its variants effectively mitigate training challenges in diffusion models by incorporating external visual representations from pretrained models.<n>We argue that the external alignment, which is absent during the entire denoising inference process, falls short of fully harnessing the potential of discriminative representations.<n>We propose Representation Entanglement for Generation (REG), which entangles low-level image latents with a single high-level class token from pretrained foundation models for denoising.
  arXiv  Detail & Related papers  (2025-07-02T08:29:18Z)
• A Scalable Approach for Safe and Robust Learning via Lipschitz-Constrained Networks [2.8960888722909566]
  Lipschitz-constrained global training constraints for neural networks (NNs) are proposed.<n>We show that the proposed formulation of Lipschitz-constrained NNs can be significantly improved.
  arXiv  Detail & Related papers  (2025-06-30T15:42:23Z)
• Stable Nonconvex-Nonconcave Training via Linear Interpolation [51.668052890249726]
  This paper presents a theoretical analysis of linearahead as a principled method for stabilizing (large-scale) neural network training. We argue that instabilities in the optimization process are often caused by the nonmonotonicity of the loss landscape and show how linear can help by leveraging the theory of nonexpansive operators.
  arXiv  Detail & Related papers  (2023-10-20T12:45:12Z)
• Efficient Bound of Lipschitz Constant for Convolutional Layers by Gram Iteration [122.51142131506639]
  We introduce a precise, fast, and differentiable upper bound for the spectral norm of convolutional layers using circulant matrix theory. We show through a comprehensive set of experiments that our approach outperforms other state-of-the-art methods in terms of precision, computational cost, and scalability. It proves highly effective for the Lipschitz regularization of convolutional neural networks, with competitive results against concurrent approaches.
  arXiv  Detail & Related papers  (2023-05-25T15:32:21Z)
• Lipschitz Continuity Retained Binary Neural Network [52.17734681659175]
  We introduce the Lipschitz continuity as the rigorous criteria to define the model robustness for BNN. We then propose to retain the Lipschitz continuity as a regularization term to improve the model robustness. Our experiments prove that our BNN-specific regularization method can effectively strengthen the robustness of BNN.
  arXiv  Detail & Related papers  (2022-07-13T22:55:04Z)
• Training Certifiably Robust Neural Networks with Efficient Local Lipschitz Bounds [99.23098204458336]
  Certified robustness is a desirable property for deep neural networks in safety-critical applications. We show that our method consistently outperforms state-of-the-art methods on MNIST and TinyNet datasets.
  arXiv  Detail & Related papers  (2021-11-02T06:44:10Z)
• Lipschitz Bounded Equilibrium Networks [3.2872586139884623]
  This paper introduces new parameterizations of equilibrium neural networks, i.e. networks defined by implicit equations. The new parameterization admits a Lipschitz bound during training via unconstrained optimization. In image classification experiments we show that the Lipschitz bounds are very accurate and improve robustness to adversarial attacks.
  arXiv  Detail & Related papers  (2020-10-05T01:00:40Z)
• On Lipschitz Regularization of Convolutional Layers using Toeplitz Matrix Theory [77.18089185140767]
  Lipschitz regularity is established as a key property of modern deep learning. computing the exact value of the Lipschitz constant of a neural network is known to be NP-hard. We introduce a new upper bound for convolutional layers that is both tight and easy to compute.
  arXiv  Detail & Related papers  (2020-06-15T13:23:34Z)
• Supervised Learning of Sparsity-Promoting Regularizers for Denoising [13.203765985718205]
  We present a method for supervised learning of sparsity-promoting regularizers for image denoising. Our experiments show that the proposed method can learn an operator that outperforms well-known regularizers.
  arXiv  Detail & Related papers  (2020-06-09T21:38:05Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.