Related papers: Robust Average Networks for Monte Carlo Denoising

We present a deep neural network to reduce coherent noise in three-dimensional quantitative phase imaging. Inspired by the cycle generative adversarial network, the denoising network was trained to learn a transform between two image…

Neural networks can be fragile to input noise and adversarial attacks. In this work, we consider Convolutional Neural Ordinary Differential Equations (NODEs), a family of continuous-depth neural networks represented by dynamical systems,…

Demosaicking and denoising are among the most crucial steps of modern digital camera pipelines and their joint treatment is a highly ill-posed inverse problem where at-least two-thirds of the information are missing and the rest are…

The emergence of deep-learning-based methods to solve image-reconstruction problems has enabled a significant increase in reconstruction quality. Unfortunately, these new methods often lack reliability and explainability, and there is a…

In recent years, a ton of research has been conducted on real image denoising tasks. However, the efforts are more focused on improving real image denoising through creating a better network architecture. We explore a different direction…

Previous works have shown that convolutional neural networks can achieve good performance in image denoising tasks. However, limited by the local rigid convolutional operation, these methods lead to oversmoothing artifacts. A deeper network…

Robustness is essential for deep neural networks, especially in security-sensitive applications. To this end, randomized smoothing provides theoretical guarantees for certifying robustness against adversarial perturbations. Recently,…

The Lipschitz constant of the map between the input and output space represented by a neural network is a natural metric for assessing the robustness of the model. We present a new method to constrain the Lipschitz constant of dense deep…

In this paper, we present DEMC, a deep Dual-Encoder network to remove Monte Carlo noise efficiently while preserving details. Denoising Monte Carlo rendering is different from natural image denoising since inexpensive by-products (feature…

Deep convolutional neural networks perform better on images containing spatially invariant degradations, also known as synthetic degradations; however, their performance is limited on real-degraded photographs and requires multiple-stage…

Deep neural networks have a great potential to improve image denoising in low-dose computed tomography (LDCT). Popular ways to increase the network capacity include adding more layers or repeating a modularized clone model in a sequence. In…

Recent years have witnessed the great success of deep convolutional neural networks (CNNs) in image denoising. Albeit deeper network and larger model capacity generally benefit performance, it remains a challenging practical issue to train…

In this paper we address the issue of output instability of deep neural networks: small perturbations in the visual input can significantly distort the feature embeddings and output of a neural network. Such instability affects many deep…

Modern digital cameras rely on the sequential execution of separate image processing steps to produce realistic images. The first two steps are usually related to denoising and demosaicking where the former aims to reduce noise from the…

Recovering an image from a noisy observation is a key problem in signal processing. Recently, it has been shown that data-driven approaches employing convolutional neural networks can outperform classical model-based techniques, because…

The development of neural networks has greatly improved the performance in various computer vision tasks. In the filed of image denoising, convolutional neural network based methods such as DnCNN break through the limits of classical…

We study the recently introduced stability training as a general-purpose method to increase the robustness of deep neural networks against input perturbations. In particular, we explore its use as an alternative to data augmentation and…

We trained denoiser autoencoding neural networks on medium resolution simulated optical spectra of late-type stars to demonstrate that the reconstruction of the original flux is possible at a typical relative error of a fraction of a…

Deep unrolling, or unfolding, is an emerging learning-to-optimize method that unrolls a truncated iterative algorithm in the layers of a trainable neural network. However, the convergence guarantees and generalizability of the unrolled…

Deep learning networks have shown state-of-the-art performance in many image reconstruction problems. However, it is not well understood what properties of representation and learning may improve the generalization ability of the network.…