SNIPS: Solving Noisy Inverse Problems Stochastically

Abstract

In this work we introduce a novel stochastic algorithm dubbed SNIPS, which draws samples from the posterior distribution of any linear inverse problem, where the observation is assumed to be contaminated by additive white Gaussian noise. Our solution incorporates ideas from Langevin dynamics and Newton's method, and exploits a pre-trained minimum mean squared error (MMSE) Gaussian denoiser. The proposed approach relies on an intricate derivation of the posterior score function that includes a singular value decomposition (SVD) of the degradation operator, in order to obtain a tractable iterative algorithm for the desired sampling. Due to its stochasticity, the algorithm can produce multiple high perceptual quality samples for the same noisy observation. We demonstrate the abilities of the proposed paradigm for image deblurring, super-resolution, and compressive sensing. We show that the samples produced are sharp, detailed and consistent with the given measurements, and their diversity exposes the inherent uncertainty in the inverse problem being solved.

arXiv commentThirty-Fifth Conference on Neural Information Processing Systems (NeurIPS), 2021

References in corpus (11)

• Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising
• LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loop
• Generative Modeling by Estimating Gradients of the Data Distribution
• The Perception-Distortion Tradeoff
• An Online Plug-and-Play Algorithm for Regularized Image Reconstruction
• Image Processing using Smooth Ordering of its Patches
• Plug-and-Play Methods Provably Converge with Properly Trained Denoisers
• LIDIA: Lightweight Learned Image Denoising with Instance Adaptation
• High Perceptual Quality Image Denoising with a Posterior Sampling CGAN
• Solving Linear Inverse Problems Using the Prior Implicit in a Denoiser
• Bayesian imaging using Plug & Play priors: when Langevin meets Tweedie