Color Image Denoising

24 papers with code • 50 benchmarks • 9 datasets

This task has no description! Would you like to contribute one?

Benchmarks

Add a Result

These leaderboards are used to track progress in Color Image Denoising

Dataset	Best Model	Compare
CBSD68 sigma50	IPT	See all
CBSD68 sigma15	ADL	See all
CBSD68 sigma25	KBNet	See all
Urban100 sigma50	Restormer-Local	See all
CBSD68 sigma35	ADL	See all
Darmstadt Noise Dataset	Image Unprocessing	See all
Kodak24 sigma50	KBNet	See all
urban100 sigma15	KBNet	See all
CBSD68 sigma75	HyperRes	See all
BSD68 sigma15	RIDNet	See all
BSD68 sigma25	RIDNet	See all
McMaster sigma50	KBNet	See all
CBSD68 sigma5	CBUIFD75	See all
Urban100 sigma25	KBNet	See all
Urban100 sigma10	Residual Dense Network +	See all
Urban100 sigma30	Restormer-Local	See all
CBSD68 sigma10	CBUIFD75	See all
CBSD68 sigma45	HyperRes	See all
CBSD68 sigma55	HyperRes	See all
CBSD68 sigma65	HyperRes	See all
RENOIR	BM3D	See all
Kodak24 sigma10	Residual Dense Network +	See all
Kodak24 sigma30	Residual Dense Network +	See all
Kodak24 sigma70	Residual Dense Network +	See all
BSD68 sigma10	Residual Dense Network +	See all
BSD68 sigma30	Residual Dense Network +	See all
BSD68 sigma70	Residual Dense Network +	See all
Urban100 sigma70	Residual Dense Network +	See all
Kodak25 sigma15	FFDNet	See all
Kodak25 sigma25	FFDNet	See all
Kodak25 sigma35	FFDNet	See all
Kodak25 sigma50	FFDNet	See all
Kodak25 sigma75	FFDNet	See all
McMaster sigma15	FFDNet	See all
McMaster sigma25	FFDNet	See all
McMaster sigma35	FFDNet	See all
McMaster sigma75	FFDNet	See all
NTIRE 2019 Real Image Denoising Challenge (sRGB)	GRDN	See all
CBSD68 sigma20	CBUIFD75	See all
CBSD68 sigma30	CBUIFD75	See all
CBSD68 sigma40	CBUIFD75	See all
CBSD68 sigma60	CBUIFD75	See all
CBSD68 sigma70	CBUIFD75	See all
BSD68 sigma5	Deep CNN Denoiser	See all
BSD68 sigma35	Deep CNN Denoiser	See all
Hanzi	DnCNN (n2t)	See all
ImageNet	DnCNN (n2t)	See all
CellNet	DnCNN (n2t)	See all
BSD68 sigma75	CSCNet	See all
CBSD68 sigma85	HyperRes	See all

Show all 50 benchmarks

Collapse benchmarks

Datasets

Most implemented papers

Most implemented Social Latest No code

Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising

cszn/DnCNN • • 13 Aug 2016

Discriminative model learning for image denoising has been recently attracting considerable attentions due to its favorable denoising performance.

Paper
Code

Residual Dense Network for Image Super-Resolution

yulunzhang/RDN • • CVPR 2018

In this paper, we propose a novel residual dense network (RDN) to address this problem in image SR. We fully exploit the hierarchical features from all the convolutional layers.

Paper
Code

Restormer: Efficient Transformer for High-Resolution Image Restoration

swz30/restormer • • CVPR 2022

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.

Paper
Code

SwinIR: Image Restoration Using Swin Transformer

jingyunliang/swinir • • 23 Aug 2021

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.

Paper
Code

FFDNet: Toward a Fast and Flexible Solution for CNN based Image Denoising

cszn/FFDNet • • 11 Oct 2017

Due to the fast inference and good performance, discriminative learning methods have been widely studied in image denoising.

Paper
Code

Pre-Trained Image Processing Transformer

huawei-noah/Pretrained-IPT • • CVPR 2021

To maximally excavate the capability of transformer, we present to utilize the well-known ImageNet benchmark for generating a large amount of corrupted image pairs.

Paper
Code

Real Image Denoising with Feature Attention

saeed-anwar/RIDNet • • ICCV 2019

Deep convolutional neural networks perform better on images containing spatially invariant noise (synthetic noise); however, their performance is limited on real-noisy photographs and requires multiple stage network modeling.

Paper
Code

Learning Deep CNN Denoiser Prior for Image Restoration

cszn/ircnn • • CVPR 2017

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).

Paper
Code