
External Prior Guided Internal Prior Learning for Real Noisy Image Denoising
Most of existing image denoising methods learn image priors from either ...
read it

Image denoising with multilayer perceptrons, part 2: training tradeoffs and analysis of their mechanisms
Image denoising can be described as the problem of mapping from a noisy ...
read it

One Size Fits All: Can We Train One Denoiser for All Noise Levels?
When training an estimator such as a neural network for tasks like image...
read it

Hyperspectral Denoising Using Unsupervised Disentangled SpatioSpectral Deep Priors
Image denoising is often empowered by accurate prior information. In rec...
read it

Robust and interpretable blind image denoising via biasfree convolutional neural networks
Deep convolutional networks often append additive constant ("bias") term...
read it

Graph Signal Recovery Using Restricted Boltzmann Machines
We propose a modelagnostic pipeline to recover graph signals from an ex...
read it

4D XRay CT Reconstruction using MultiSlice Fusion
There is an increasing need to reconstruct objects in four or more dimen...
read it
Deep Denoising: RateOptimal Recovery of Structured Signals with a Deep Prior
Deep neural networks provide stateoftheart performance for image denoising, where the goal is to map a noisy image to a near noisefree image. The underlying principle is simple: images are well described by priors that map a lowdimensional latent representations to image. Based on a prior, a noisy image can be denoised by finding a close image in the range of the prior. Since deep networks trained on large set of images have empirically been shown to be good priors, they enable effective denoisers. However, there is little theory to justify this success, let alone to predict the denoising performance. In this paper we consider the problem of denoising an image from additive Gaussian noise with variance σ^2, assuming the image is well described by a deep neural network with ReLu activations functions, mapping a kdimensional latent space to an ndimensional image. We provide an iterative algorithm minimizing a nonconvex loss that provably removes noise energy by a fraction σ^2 k/n. We also demonstrate in numerical experiments that this denoising performance is, indeed, achieved by generative priors learned from data.
READ FULL TEXT
Comments
There are no comments yet.