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 1051–1100 of 7282 papers

TitleStatusHype
Mask prior-guided denoising diffusion improves inverse protein foldingCode1
Mobile Video Diffusion—0
Video Motion Transfer with Diffusion TransformersCode2
Modeling Dual-Exposure Quad-Bayer Patterns for Joint Denoising and DeblurringCode1
A Progressive Image Restoration Network for High-order Degradation Imaging in Remote Sensing—0
Fast Track to Winning Tickets: Repowering One-Shot Pruning for Graph Neural NetworksCode0
Paired Wasserstein Autoencoders for Conditional Sampling—0
Anomaly detection using Diffusion-based methods—0
ACDiT: Interpolating Autoregressive Conditional Modeling and Diffusion TransformerCode1
Diverse Score Distillation—0
Echocardiography to Cardiac MRI View Transformation for Real-Time Blind Restoration—0
Efficiency Meets Fidelity: A Novel Quantization Framework for Stable Diffusion—0
Generative Lines Matching Models—0
ASGDiffusion: Parallel High-Resolution Generation with Asynchronous Structure Guidance—0
A CT Image Denoising Method Based on Projection Domain Feature—0
Around the World in 80 Timesteps: A Generative Approach to Global Visual GeolocationCode3
You KAN Do It in a Single Shot: Plug-and-Play Methods with Single-Instance Priors—0
CARP: Visuomotor Policy Learning via Coarse-to-Fine Autoregressive Prediction—0
BudgetFusion: Perceptually-Guided Adaptive Diffusion Models—0
Accelerating Video Diffusion Models via Distribution Matching—0
FlexDiT: Dynamic Token Density Control for Diffusion TransformerCode1
Tiny Object Detection with Single Point Supervision—0
3D-Consistent Image Inpainting with Diffusion Models—0
Enhanced 3D Generation by 2D Editing—0
Adversarial Transferability in Deep Denoising Models: Theoretical Insights and Robustness Enhancement via Out-of-Distribution Typical Set Sampling—0
Graph with Sequence: Broad-Range Semantic Modeling for Fake News Detection—0
Enhancing Sample Generation of Diffusion Models using Noise Level Correction—0
Remix-DiT: Mixing Diffusion Transformers for Multi-Expert DenoisingCode1
A Comparative Study of Image Denoising Algorithms—0
Equivariant Denoisers for Image Restoration—0
Customized Generation Reimagined: Fidelity and Editability HarmonizedCode1
The Silent Prompt: Initial Noise as Implicit Guidance for Goal-Driven Image Generation—0
Latent Space Characterization of Autoencoder Variants—0
Learning to Translate Noise for Robust Image DenoisingCode1
SceneDiffuser: Efficient and Controllable Driving Simulation Initialization and Rollout—0
Generalized Recorrupted-to-Recorrupted: Self-Supervised Learning Beyond Gaussian NoiseCode4
INFP: Audio-Driven Interactive Head Generation in Dyadic Conversations—0
Local Curvature Smoothing with Stein's Identity for Efficient Score Matching—0
A Data-Driven Framework for Discovering Fractional Differential Equations in Complex Systems—0
Deep priors for satellite image restoration with accurate uncertainties—0
Hipandas: Hyperspectral Image Joint Denoising and Super-Resolution by Image Fusion with the Panchromatic Image—0
A Noise is Worth Diffusion Guidance—0
Partially Conditioned Patch Parallelism for Accelerated Diffusion Model Inference—0
UTSD: Unified Time Series Diffusion Model—0
Imagine360: Immersive 360 Video Generation from Perspective Anchor—0
Assessing the performance of CT image denoisers using Laguerre-Gauss Channelized Hotelling Observer for lesion detection—0
TASR: Timestep-Aware Diffusion Model for Image Super-ResolutionCode1
End-to-end Triple-domain PET Enhancement: A Hybrid Denoising-and-reconstruction Framework for Reconstructing Standard-dose PET Images from Low-dose PET Sinograms—0
Grayscale to Hyperspectral at Any Resolution Using a Phase-Only Lens—0
Diffusion-based Visual Anagram as Multi-task LearningCode2
Show:102550
← PrevPage 22 of 146Next →
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