arXiv subjects

Trishit Mukherjee

Publications and source records attributed to Trishit Mukherjee.

3 recordsLinked to original sources

arXiv2026

Stabilizing Deep Reconstruction Operators with Contractive Anchoring

Pretrained deep denoisers can be used to solve a wide range of model-based image reconstruction tasks via Plug-and-Play (PnP) and Regularization-by-Denoising (RED) algorithms, without retraining per task. These denoisers are trained only for single-step denoising. Using them as Image Reconstruction (IR) regularizers in an iterative process can destabilize reconstruction. A common failure mode is the peak-and-collapse behaviour: metrics such as PSNR improve for early iterations and then abruptly degrade, making these algorithms unreliable in practice. We propose a data-driven stabilization framework that (i) formalizes this instability of any IR operator through a local quantity and (ii) prevents collapse by regularizing this quantity adaptively, requiring no retraining or modification of the given pretrained network. Our key idea is to control the potentially unstable IR operator with a contractive operator whose stable iterates act as an anchor and prevent collapse. We further introduce an efficient family of trainable contractive operators that serve as strong anchors while remaining lightweight. Extensive experiments across proximal algorithms, denoiser architectures, noise levels, and imaging tasks show consistent, collapse-free performance and improved reliability of PnP and RED reconstruction.

eess.IV↗

arXiv2026

Trainable Nonexpansive Denoisers for Contractive Image Reconstruction

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.

eess.IV↗

arXiv2025

Viscosity Stabilized Plug-and-Play Reconstruction

The plug-and-play (PnP) method uses a deep denoiser within a proximal algorithm for model-based image reconstruction (IR). Unlike end-to-end IR, PnP allows the same pretrained denoiser to be used across different imaging tasks, without the need for retraining. However, black-box networks can make the iterative process in PnP unstable. A common issue observed across architectures like CNNs, diffusion models, and transformers is that the visual quality and PSNR often improve initially but then degrade in later iterations. Previous attempts to ensure stability usually impose restrictive constraints on the denoiser. However, standard denoisers, which are freely trained for single-step noise removal, need not satisfy such constraints. We propose a simple data-driven stabilization mechanism that adaptively averages the potentially unstable PnP operator with a contractive IR operator. This acts as a form of viscosity regularization, where the contractive component progressively dampens updates in later iterations, helping to suppress oscillations and prevent divergence. We validate the effectiveness of our stabilization mechanism across different proximal algorithms, denoising architectures, and imaging tasks.

eess.IV↗