Denoising
1893 papers with code • 5 benchmarks • 20 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 )
Benchmarks
These leaderboards are used to track progress in Denoising
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
|||||
|
|||||
|
Libraries
Use these libraries to find Denoising models and implementations
SIDD
SID
CBSD68
PolyU
DND
CRVD
iris
FMD
Subtasks
Most implemented papers
Neighbor2Neighbor: Self-Supervised Denoising from Single Noisy Images
TaoHuang2018/Neighbor2Neighbor
•
•
CVPR 2021
In this paper, we present a very simple yet effective method named Neighbor2Neighbor to train an effective image denoising model with only noisy images.
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.
Restormer: Efficient Transformer for High-Resolution Image Restoration
Since convolutional neural networks (CNNs) perform well at learning generalizable image priors from large-scale data, these models have been extensively applied to image restoration and related tasks.
Low Dose CT Image Denoising Using a Generative Adversarial Network with Wasserstein Distance and Perceptual Loss
In this paper, we introduce a new CT image denoising method based on the generative adversarial network (GAN) with Wasserstein distance and perceptual similarity.
SwinIR: Image Restoration Using Swin Transformer
In particular, the deep feature extraction module is composed of several residual Swin Transformer blocks (RSTB), each of which has several Swin Transformer layers together with a residual connection.
Simple Baselines for Image Restoration
Although there have been significant advances in the field of image restoration recently, the system complexity of the state-of-the-art (SOTA) methods is increasing as well, which may hinder the convenient analysis and comparison of methods.
CycleISP: Real Image Restoration via Improved Data Synthesis
This is mainly because the AWGN is not adequate for modeling the real camera noise which is signal-dependent and heavily transformed by the camera imaging pipeline.
Multi-Stage Progressive Image Restoration
At each stage, we introduce a novel per-pixel adaptive design that leverages in-situ supervised attention to reweight the local features.
Iterative Gaussianization: from ICA to Random Rotations
IPL-UV/rbig_jax
•
•
IEEE Transactions on Neural Networks 2011
The practical performance of RBIG is successfully illustrated in a number of multidimensional problems such as image synthesis, classification, denoising, and multi-information estimation.
FFDNet: Toward a Fast and Flexible Solution for CNN based Image Denoising
cszn/FFDNet
•
•
Due to the fast inference and good performance, discriminative learning methods have been widely studied in image denoising.
