6 papers
Trainable Nonexpansive Denoisers for Contractive Image Reconstruction
Arghya Sinha, Aditya Banerjee, Trishit Mukherjee +1
Trainable denoisers with Lipschitz control have become central to convergent image reconstruction. However, training neural networks that simultaneously offer strong denoising perf…
Stabilizing Deep Reconstruction Operators with Contractive Anchoring
Arghya Sinha, Trishit Mukherjee, Kunal N. Chaudhury
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, with…
Viscosity Stabilized Plug-and-Play Reconstruction
Arghya Sinha, Trishit Mukherjee, Kunal N. Chaudhury
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 deno…
Linear Convergence of Plug-and-Play Algorithms with Kernel Denoisers
Arghya Sinha, Bhartendu Kumar, Chirayu D. Athalye +1
The use of denoisers for image reconstruction has shown significant potential, especially for the Plug-and-Play (PnP) framework. In PnP, a powerful denoiser is used as an implicit…
FISTA Iterates Converge Linearly for Denoiser-Driven Regularization
Arghya Sinha, Kunal N. Chaudhury
The effectiveness of denoising-driven regularization for image reconstruction has been widely recognized. Two prominent algorithms in this area are Plug-and-Play () a…
On the Strong Convexity of PnP Regularization Using Linear Denoisers
Arghya Sinha, Kunal N Chaudhury
In the Plug-and-Play (PnP) method, a denoiser is used as a regularizer within classical proximal algorithms for image reconstruction. It is known that a broad class of linear denoi…