Denoising
2405 papers with code • 6 benchmarks • 21 datasets
Denoising is a task in image processing and computer vision that aims to remove or reduce noise from an image. Noise can be introduced into an image due to various reasons, such as camera sensor limitations, lighting conditions, and compression artifacts. The goal of denoising is to recover the original image, which is considered to be noise-free, from a noisy observation.
( Image credit: Beyond a Gaussian Denoiser )
Libraries
Use these libraries to find Denoising models and implementationsSubtasks
Most implemented papers
Denoising Diffusion Probabilistic Models
We present high quality image synthesis results using diffusion probabilistic models, a class of latent variable models inspired by considerations from nonequilibrium thermodynamics.
BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension
We evaluate a number of noising approaches, finding the best performance by both randomly shuffling the order of the original sentences and using a novel in-filling scheme, where spans of text are replaced with a single mask token.
High-Resolution Image Synthesis with Latent Diffusion Models
By decomposing the image formation process into a sequential application of denoising autoencoders, diffusion models (DMs) achieve state-of-the-art synthesis results on image data and beyond.
Denoising Diffusion Implicit Models
Denoising diffusion probabilistic models (DDPMs) have achieved high quality image generation without adversarial training, yet they require simulating a Markov chain for many steps to produce a sample.
Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising
Discriminative model learning for image denoising has been recently attracting considerable attentions due to its favorable denoising performance.
Noise2Noise: Learning Image Restoration without Clean Data
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.
Learning to See in the Dark
Imaging in low light is challenging due to low photon count and low SNR.
Image Restoration Using Convolutional Auto-encoders with Symmetric Skip Connections
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.
Improved Denoising Diffusion Probabilistic Models
Denoising diffusion probabilistic models (DDPM) are a class of generative models which have recently been shown to produce excellent samples.
Deep Image Prior
In this paper, we show that, on the contrary, the structure of a generator network is sufficient to capture a great deal of low-level image statistics prior to any learning.