Denoising

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 )

Papers

Recently Added Most Hyped Most Active Needs Verification Most Verified

Showing 2811–2820 of 7282 papers

Title	Date	Tasks	Status	Score
Fine-grained Forecasting Models Via Gaussian Process Blurring Effect	Dec 21, 2023	DenoisingImage Generation	CodeCode Available	5
Unsupervisedly Prompting AlphaFold2 for Few-Shot Learning of Accurate Folding Landscape and Protein Structure Prediction	Aug 20, 2022	DenoisingFew-Shot Learning	CodeCode Available	5
Few-shot point cloud reconstruction and denoising via learned Guassian splats renderings and fine-tuned diffusion features	Apr 1, 2024	3D ReconstructionDeep Learning	CodeCode Available	5
Few-shot Image Generation with Diffusion Models	Nov 7, 2022	DenoisingDiversity	CodeCode Available	5
FFDNet: Toward a Fast and Flexible Solution for CNN based Image Denoising	Oct 11, 2017	Color Image DenoisingCPU	CodeCode Available	5
A denoised Mean Teacher for domain adaptive point cloud registration	Jun 26, 2023	Computational EfficiencyDenoising	CodeCode Available	5
FEUNet: a flexible and effective U-shaped network for image denoising	Jan 16, 2023	DenoisingImage Denoising	CodeCode Available	5
FedFTN: Personalized Federated Learning with Deep Feature Transformation Network for Multi-institutional Low-count PET Denoising	Apr 2, 2023	DenoisingFederated Learning	CodeCode Available	5
Few Clean Instances Help Denoising Distant Supervision	Sep 14, 2022	Denoising	CodeCode Available	5
DiffSmooth: Certifiably Robust Learning via Diffusion Models and Local Smoothing	Aug 28, 2023	Adversarial PurificationDenoising	CodeCode Available	5

Show:10 25 50

← PrevPage 282 of 729Next →

All datasets Darmstadt Noise Dataset DIV2K DND iris

Benchmark Results

#	Model	Metric	Claimed	Verified	Status
1	SINDy	PSNR	81	—	Unverified
2	Pixel-shuffling Downsampling	PSNR	38.4	—	Unverified
3	TWSC	PSNR	37.93	—	Unverified
4	CBDNet(Syn)	PSNR	37.57	—	Unverified
5	MCWNNM	PSNR	37.38	—	Unverified
6	Han et al	PSNR	35.95	—	Unverified
7	FFDNet	PSNR	34.4	—	Unverified
8	TNRD	PSNR	33.65	—	Unverified
9	CDnCNN-B	PSNR	32.43	—	Unverified
10	NLRN	PSNR	30.8	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	DRUnet_Poisson_0.01	Average PSNR (dB)	33.92	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	DRANet	Average PSNR	39.64	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	PCNN+RL+HME	Average	84.61	—	Unverified