Denoising is the task of removing noise from an image.
In this work, we propose a very deep fully convolutional auto-encoder network for image restoration, which is a encoding-decoding framework with symmetric convolutional-deconvolutional layers.
SOTA for Image Denoising on BSD200 sigma10
Discriminative model learning for image denoising has been recently attracting considerable attentions due to its favorable denoising performance.
#2 best model for Image Denoising on BSD68 sigma10
We apply basic statistical reasoning to signal reconstruction by machine learning -- learning to map corrupted observations to clean signals -- with a simple and powerful conclusion: it is possible to learn to restore images by only looking at corrupted examples, at performance at and sometimes exceeding training using clean data, without explicit image priors or likelihood models of the corruption.
Recent works have revealed that, with the aid of variable splitting techniques, denoiser prior can be plugged in as a modular part of model-based optimization methods to solve other inverse problems (e. g., deblurring).
#4 best model for Image Denoising on BSD68 sigma15
To exploit our relaxation, we propose the neural nearest neighbors block (N3 block), a novel non-local processing layer that leverages the principle of self-similarity and can be used as building block in modern neural network architectures.
#2 best model for Image Denoising on Urban100 sigma70
While deep convolutional neural networks (CNNs) have achieved impressive success in image denoising with additive white Gaussian noise (AWGN), their performance remains limited on real-world noisy photographs.
Distantly supervised open-domain question answering (DS-QA) aims to find answers in collections of unlabeled text.
#2 best model for Open-Domain Question Answering on Quasar