SOTAVerified

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 AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 2776–2800 of 7282 papers

TitleStatusHype
X-Adapter: Adding Universal Compatibility of Plugins for Upgraded Diffusion Model—0
EMDM: Efficient Motion Diffusion Model for Fast and High-Quality Motion GenerationCode1
DiffiT: Diffusion Vision Transformers for Image GenerationCode2
Fully Spiking Denoising Diffusion Implicit ModelsCode1
Unsupervised Anomaly Detection using Aggregated Normative DiffusionCode1
ResEnsemble-DDPM: Residual Denoising Diffusion Probabilistic Models for Ensemble Learning—0
Equivariant plug-and-play image reconstruction—0
Slice3D: Multi-Slice, Occlusion-Revealing, Single View 3D Reconstruction—0
A Conditional Denoising Diffusion Probabilistic Model for Point Cloud UpsamplingCode1
AAMDM: Accelerated Auto-regressive Motion Diffusion Model—0
Planning as In-Painting: A Diffusion-Based Embodied Task Planning Framework for Environments under UncertaintyCode1
LDM-ISP: Enhancing Neural ISP for Low Light with Latent Diffusion Models—0
DeepCache: Accelerating Diffusion Models for FreeCode2
SynFundus-1M: A High-quality Million-scale Synthetic fundus images Dataset with Fifteen Types of AnnotationCode1
HiFi Tuner: High-Fidelity Subject-Driven Fine-Tuning for Diffusion Models—0
Layered Rendering Diffusion Model for Controllable Zero-Shot Image SynthesisCode0
On Exact Inversion of DPM-Solvers—0
Contrastive Denoising Score for Text-guided Latent Diffusion Image EditingCode1
Diffusion Models Without Attention—0
CAT-DM: Controllable Accelerated Virtual Try-on with Diffusion ModelCode1
Accurate Segmentation of Optic Disc And Cup from Multiple Pseudo-labels by Noise-aware LearningCode0
Unsupervised Keypoints from Pretrained Diffusion ModelsCode1
Improving Interpretation Faithfulness for Vision Transformers—0
SODA: Bottleneck Diffusion Models for Representation LearningCode1
MagDiff: Multi-Alignment Diffusion for High-Fidelity Video Generation and EditingCode1
Show:102550
← PrevPage 112 of 292Next →
All datasetsDarmstadt Noise DatasetDIV2KDNDiris

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1SINDyPSNR81—Unverified
2Pixel-shuffling DownsamplingPSNR38.4—Unverified
3TWSCPSNR37.93—Unverified
4CBDNet(Syn)PSNR37.57—Unverified
5MCWNNMPSNR37.38—Unverified
6Han et alPSNR35.95—Unverified
7FFDNetPSNR34.4—Unverified
8TNRDPSNR33.65—Unverified
9CDnCNN-BPSNR32.43—Unverified
10NLRNPSNR30.8—Unverified
#ModelMetricClaimedVerifiedStatus
1DRUnet_Poisson_0.01Average PSNR (dB)33.92—Unverified
#ModelMetricClaimedVerifiedStatus
1DRANetAverage PSNR39.64—Unverified
#ModelMetricClaimedVerifiedStatus
1PCNN+RL+HMEAverage84.61—Unverified