The interest of the machine learning community in image synthesis has grown significantly in recent years, with the introduction of a wide range of deep generative models and means for training them.
Ranked #2 on Image Generation on ImageNet 128x128
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 algorithm augments video sequences with patch-craft frames and feeds them to a CNN.
Ranked #2 on Video Denoising on DAVIS sigma20
We showcase our proposed method with a novel denoiser architecture that achieves the reformed denoising goal and produces vivid and diverse outcomes in immoderate noise levels.
Image denoising is a well-known and well studied problem, commonly targeting a minimization of the mean squared error (MSE) between the outcome and the original image.
A popular representative of this approach is the Iterative Shrinkage-Thresholding Algorithm (ISTA) and its learned version -- LISTA, aiming for the sparse representations of the processed signals.
In this work we aim to break the unholy connection between bit-rate and image quality, and propose a way to circumvent compression artifacts by pre-editing the incoming image and modifying its content to fit the given bits.
Neural networks that are based on unfolding of an iterative solver, such as LISTA (learned iterative soft threshold algorithm), are widely used due to their accelerated performance.
This work proposes a novel lightweight learnable architecture for image denoising, and presents a combination of supervised and unsupervised training of it, the first aiming for a universal denoiser and the second for adapting it to the incoming image.
Sparse representation with respect to an overcomplete dictionary is often used when regularizing inverse problems in signal and image processing.
Ranked #1 on Color Image Denoising on BSD68 sigma75
Inverse problems in imaging are extensively studied, with a variety of strategies, tools, and theory that have been accumulated over the years.
Ranked #7 on Image Super-Resolution on Set14 - 8x upscaling
Instead of feeding the network with synthetic data, we solely use real-world outdoor images and tune the network's parameters by directly minimizing the DCP.
Ranked #9 on Image Dehazing on SOTS Outdoor
The Convolutional Sparse Coding (CSC) model has recently gained considerable traction in the signal and image processing communities.
The proposed method adds controlled noise to the input and estimates a sparse representation from the perturbed signal.
Modern data introduces new challenges to classic signal processing approaches, leading to a growing interest in the field of graph signal processing.
The success of deep learning has been due, in no small part, to the availability of large annotated datasets.
Ranked #10 on Image Dehazing on SOTS Outdoor
Despite their impressive performance, deep convolutional neural networks (CNNs) have been shown to be sensitive to small adversarial perturbations.
We show that the training of the filters is essential to allow for non-trivial signals in the model, and we derive an online algorithm to learn the dictionaries from real data, effectively resulting in cascaded sparse convolutional layers.
Convolutional Sparse Coding (CSC) is an increasingly popular model in the signal and image processing communities, tackling some of the limitations of traditional patch-based sparse representations.
The traditional sparse modeling approach, when applied to inverse problems with large data such as images, essentially assumes a sparse model for small overlapping data patches.
As opposed to the $P^3$ method, we offer Regularization by Denoising (RED): using the denoising engine in defining the regularization of the inverse problem.
Compressed Learning (CL) is a joint signal processing and machine learning framework for inference from a signal, using a small number of measurements obtained by linear projections of the signal.
In this paper, we propose a supervised dictionary learning algorithm that aims to preserve the local geometry in both dimensions of the data.
Image and texture synthesis is a challenging task that has long been drawing attention in the fields of image processing, graphics, and machine learning.
Recent work on this problem adopting Convolutional Neural-networks (CNN) ignited a renewed interest in this field, due to the very impressive results obtained.
This is shown to be tightly connected to CNN, so much so that the forward pass of the CNN is in fact the thresholding pursuit serving the ML-CSC model.
Compressed sensing (CS) is a signal processing framework for efficiently reconstructing a signal from a small number of measurements, obtained by linear projections of the signal.
Therefore, with a minor increase of the dimensions (e. g. with additional 10 values to the patch representation), we implicitly/softly describe the information of a large patch.
Recent work in image processing suggests that operating on (overlapping) patches in an image may lead to state-of-the-art results.
Sparse representations has shown to be a very powerful model for real world signals, and has enabled the development of applications with notable performance.
In this work we suggest a novel method for coupling Gaussian denoising algorithms to Poisson noisy inverse problems, which is based on a general approach termed "Plug-and-Play".
This paper proposes a simple, accurate, and robust approach to single image nonparametric blind Super-Resolution (SR).
In this paper, we propose a simple, effective and fast approach for the estimation of the motion blur-kernel, through a bi-l0-l2-norm regularization imposed on both the intermediate sharp image and the blur-kernel.
Two complementary approaches have been extensively used in signal and image processing leading to novel results, the sparse representation methodology and the variational strategy.
We propose a supervised machine learning approach for boosting existing signal and image recovery methods and demonstrate its efficacy on example of image reconstruction in computed tomography.